Fast Detection System Research Articles

Electrochemical Detection of DNA in Agriculture Using Lamp-Based Amplification

The variety and complexity of genetically modified organisms (GMOs) are increasing, which makes their detection harder than ever before. This impacts the traceability, safety, and monitoring of food. Current research indicates that GM crop technology may pose risks to human health and the environment. The aim of this study is the development of a LAMP-based GMO electrochemical detection device. LAMP amplification of P-35S, P-FMV, and T-NOS regions (three elements that are most often present in genetically modified plants as part of the transgenic construct) is done using gBlocks, synthetic dsDNA fragments that have an identical DNA sequence to that of the targeted part of a transgenic construct.Using single-stranded DNA probes containing methylene blue as a redox probe, the electrochemical DNA sensor detects LAMP products that are complementary to the target DNA. The probes were attached to the gold electrodes functionalized by gold nanoparticles, and 2D nanomaterials (MoS2, Mxenes, and reduced graphene oxide). The electrochemical methods, such as alternating current voltammetry, square wave voltammetry, and differential pulse voltammetry were employed in testing the electrochemical detection response of the DNA probes immobilized on 2D nanomaterials.The research has shown that the obtained DNA detection signal depends significantly on the methods (and setup parameters) used in electrochemical detection, and the nanomaterials used on electrodes. The electrochemical detection resulted in a signal decrease consequential to the conformational changes of the DNA probes upon attachment of the target DNA. The methylene blue molecules attached at the top of the DNA probes get higher resistance in the electron transfer to the electrode materials, which makes the target DNA detection quantitatively and qualitatively visible. These results are promising for the development of a device that will enable a specific, sensitive, fast, cost-effective, and precise in-field detection system for the routine detection of GMOs.**Acknowledgments:*This project is supported by The Science Fund of the Republic of Serbia DEVELOPMENT Program - Green program of cooperation between science and industry - LABOUR project (grant agreement No. 6710), and The Ministry of Science, Technological Development and Innovation of the Republic of Serbia (451-03-66/2024-03/200358).*This work is supported through the ANTARES project that has received funding from the European Union's Horizon 2020 research and innovation program under grant agreement SGA-CSA. No. 739570 under FPA No. 664387. https://doi.org/10.3030/739570 Figure 1

COVID-19 detection from exhaled breath

The SARS-CoV-2 coronavirus emerged in 2019 causing a COVID-19 pandemic that resulted in 7 million deaths out of 770 million reported cases over the next 4 years. The global health emergency called for unprecedented efforts to monitor and reduce the rate of infection, pushing the study of new diagnostic methods. In this paper, we introduce a cheap, fast, and non-invasive COVID-19 detection system, which exploits only exhaled breath. Specifically, provided an air sample, the mass spectra in the 10–351 mass-to-charge range are measured using an original micro and nano-sampling device coupled with a high-precision spectrometer; then, the raw spectra are processed by custom software algorithms; the clean and augmented data are eventually classified using state-of-the-art machine-learning algorithms. An uncontrolled clinical trial was conducted between 2021 and 2022 on 302 subjects who were concerned about being infected, either due to exhibiting symptoms or having recently recovered from illness. Despite the simplicity of use, our system showed a performance comparable to the traditional polymerase-chain-reaction and antigen testing in identifying cases of COVID-19 (that is, 95% accuracy, 94% recall, 96% specificity, and 92% \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$F_1$$\\end{document}-score). In light of these outcomes, we think that the proposed system holds the potential for substantial contributions to routine screenings and expedited responses during future epidemics, as it yields results comparable to state-of-the-art methods, providing them in a more rapid and less invasive manner.

B-216 Ethanol/isopropanol-free and enzyme-free universal nucleic acid extraction and purification system for fast molecular detection from swab samples

Abstract Background Efficient nucleic acid (NA) extraction has been made technology advancement in molecular science. However, there are several challenges yet to address. Firstly, ethanol or isopropanol are important components of the buffers for the most commercially available NA extraction kits. When put on cartridge for POC applications, they can react with plastic materials, undermining their mechanical/physiochemical properties. They can also be problematic due to their volatility, flammability and potential to leak. Secondly, turn-around time for most commercial kits is long and procedure is rather tedious. Thirdly, most of the extraction buffers can only be used to extract either DNA or RNA from either viruses or bacteria. A universal buffer system is lacking. Lastly, special components in some extraction buffers require -20°C or 4°C storage for desired performance, especially for those kits containing proteinase for cell lysis and nuclease denaturation and carrier NA for low quantity of template, causing inconvenience in shipping and storage. Delta developed buffers and associated protocol to address the challenges listed above. This study is to evaluate the performance of the Delta TNA buffer system in NA extraction and purification from various target pathogens in swab samples when compared to that of the leading commercial products. Methods The stock strains of staphylococcus aureus, pseudomonas aeruginosa and H-coronavirus OC43 were diluted in Delta Molecular Transport Media containing swab sample matrix to the testing concentrations before performing NA extraction. Vircell SARS-CoV-2 RNA was spiked directly into PCR reactions to generate a standard curve with 10x serial dilutions for the recovery rate test using Delta TNA kit. 300ul of samples were used for the NA extraction and purification with 80 ul eluate generated. The manufacturers’ instructions were followed. The extracted RNA or DNA was amplified on BioRAD CFX96. Results The extraction efficiency on RNA from H-coronavirus OC43, DNA from pseudomonas aeruginosa and staphylococcus aureus in swab samples, was compared with Katsura Respi and MN Pathogen kits, Qiagen DNA and viral RNA kits respectively. Delta TNA kit outperformed in either earlier Cq value or higher detection rate for different concentrations of analytes in <10 min comparing to up to 95 min for the commercial kits tested. The RNA recovery rate of Delta TNA kit was comparable to that of the Qiagen Viral Kit with 37.54% vs 29.84% at 10 copies/rxn, 146.84% vs 140.76% at 100 cpies/rxn and 118.29% vs 111.76% at 1000 copies/rxn. Meanwhile, Delta Swab TNA buffer was compatible with large spectrum of magnetic beads possessing various coating groups and particle sizes. Conclusions We provided a stable, user- and environment-friendly total nucleic acid extraction and purification system which is ethanol/isopropanol-free and enzyme-free. There is no pre-treatment or drying steps in the protocol and no centrifugation required. Delta’s protocol has the least total number of steps and least amount of total time taken amongst the kits compared. It serves as a universal recipe for both DNA and RNA from pathogens in swab samples including viruses and bacteria in less than 10 min, with competitive performance in both PCR and LAMP.

Real-Time Object Detection and Tracking for Occupational Health and Safety (OHS) in Mining Operations Using Streamed CCTV Data

Abstract Occupational Safety and Health (OHS) is very important in the mining industry which is prone to accident risks. Automatic detection of violations through CCTV streaming with the concept of a perimeter area is needed to prevent accidents. The purpose of this research is to create a violation detection system without re-modeling training that can adapt to different objects and regions. The proposed violation detection model includes four computational steps, namely (i) data reading, (ii) data pre-processing, (iii) object detection, and (iv) object tracking and violation detection. The computer vision technique uses the SIFT (Scale Invariant Feature Transform) algorithm and heuristics implemented with OpenCV. We used five CCTV video recordings of mining operations as examples. The results showed an average precision of 61.14%, a precision of 80.41%, and a recall of 69.38%. The average computation time of the model is 0.3 seconds per frame with heuristics that allow the model to be used in real-time. The model can be widely used in various fields and locations without having to retrain the model to improve OHS in the mining industry and other sectors with similar risks. This study will contribute to the development of a flexible, fast, and real-time automatic detection system.

Mosquitoes on a chip-environmental DNA-based detection of invasive mosquito species using high-throughput real-time PCR.

The monitoring of mosquitoes is of great importance due to their vector competence for a variety of pathogens, which have the potential to imperil human and animal health. Until now mosquito occurrence data is mainly obtained with conventional monitoring methods including active and passive approaches, which can be time- and cost-consuming. New monitoring methods based on environmental DNA (eDNA) could serve as a fast and robust complementary detection system for mosquitoes. In this pilot study already existing marker systems targeting the three invasive mosquito species Aedes (Ae.) albopictus, Ae. japonicus and Ae. koreicus were used to detect these species from water samples via microfluidic array technology. We compared the performance of the high-throughput real-time PCR (HT-qPCR) system Biomark HD with real-time PCR (qPCR) and also tested the effect of different filter media (Sterivex® 0.45 µm, Nylon 0.22 µm, PES 1.2 µm) on eDNA detectability. By using a universal qPCR protocol and only 6-FAM-MGB probes we successfully transferred these marker systems on the HT-qPCR platform. All tested marker systems detected the target species at most sites, where their presence was previously confirmed. Filter media properties, the final filtration volume and observed qPCR inhibition did not affect measured Ct values via qPCR or HT-qPCR. The Ct values obtained from HT-qPCR were significantly lower as Ct values measured by qPCR due to the previous preamplification step, still these values were highly correlated. Observed incongruities in eDNA detection probability, as manifested by non-reproducible results and false positive detections, could be the result of methodological aspects, such as sensitivity and specificity issues of the used assays, or ecological factors such as varying eDNA release patterns. In this study, we show the suitability of eDNA-based detection of mosquito species from water samples using a microfluidic HT-qPCR platform. HT-qPCR platforms such as Biomark HD allow for massive upscaling of tested species-specific assays and sampling sites with low time- and cost-effort, thus this methodology could serve as basis for large-scale mosquito monitoring attempts. The main goal in the future is to develop a robust (semi)-quantitative microfluidic-based eDNA mosquito chip targeting all haematophagous culicid species occurring in Western Europe. This chip would enable large-scale eDNA-based screenings to assess mosquito diversity, to monitor species with confirmed or suspected vector competence, to assess the invasion progress of invasive mosquito species and could be used in pathogen surveillance, when disease agents are incorporated.

Development and application of a low-cost and portable multi-channel spectral detection system for mutton adulteration

It is important to develop low-cost, fast and portable meat adulteration detection systems to ensure the meat authenticity and safety in complex market environments. A multi-channel spectral detection system for meat adulteration was developed in this study. The core hardware of the system mainly includes a designed spectral module and a Raspberry pi controller. The spectral module consists of three multi-channel spectral sensors and LED lamps with specific wavelengths, containing 18 channels covering a range of 410–940 nm. The software was developed based on PyQt5. After completing the construction of the system, the detection distance was discussed and determined to be 4 mm. Based on the spectral data collected by the developed system, the models for classifying pure mutton, pure pork, mutton flavour essence adulteration, colourant adulteration and adulterated mutton with pork were established and compared. Four intelligent optimisation algorithms were further used to improve the model performance. The results of the test set showed that the support vector classification (SVC) model optimised by a sparrow search algorithm (SSA) obtained the best classification performance, with an accuracy of 97.59% and a Kappa coefficient of 0.9696. After the SSA-SVC was incorporated into the sensor software, the system performance was evaluated using external validation samples. The overall accuracy of the system was 94.29%. The system took about 5.31 s to detect a sample, and the total weight of the system was 1.55 kg. Overall, the developed portable spectral system has considerable potential to rapidly and accurately discriminate adulterated mutton in the field.

Sensitive determination of Gabapentin in plasma sample using dispersive liquid-liquid microextraction coupled with ion mobility spectrometry

Gabapentin (GBP) is an anticonvulsant agent and its determination using a fast and simple method is challenging. In this research, a novel sensitive, and economical method for the fast determination of GBP in biological samples was developed. This method benefits from the advantages of ion mobility spectrometry (IMS) as a fast detection and separation system and dispersive liquid-liquid microextraction (DLLME) for the preconcentration/extraction of GBP. In the developed method (DLLME-IMS), Ag nanoparticles serve as modifiers. Moreover, the quantum theory of atoms in molecules (QTAIM) analysis was employed to investigate the interaction mechanism between GBP and Ag nanoparticles. Also, a delay time after the injection of the sample was applied to improve the method sensitivity. Under the optimum condition, the developed method showed a linear response over the concentration range of 0.3–12 μg mL−1 and a detection limit of 0.12 μg mL−1. Eventually, DLLME-IMS was successfully employed in plasma sample, and was validated against the HPLC method with UV detection as a reference method. The developed method will open up a new avenue for the development of effective, rapid, and simple analytical methods.

An Improved Ningxia Desert Herbaceous Plant Classification Algorithm Based on YOLOv8.

Wild desert grasslands are characterized by diverse habitats, uneven plant distribution, similarities among plant class, and the presence of plant shadows. However, the existing models for detecting plant species in desert grasslands exhibit low precision, require a large number of parameters, and incur high computational cost, rendering them unsuitable for deployment in plant recognition scenarios within these environments. To address these challenges, this paper proposes a lightweight and fast plant species detection system, termed YOLOv8s-KDT, tailored for complex desert grassland environments. Firstly, the model introduces a dynamic convolutional KernelWarehouse method to reduce the dimensionality of convolutional kernels and increase their number, thus achieving a better balance between parameter efficiency and representation ability. Secondly, the model incorporates triplet attention into its feature extraction network, effectively capturing the relationship between channel and spatial position and enhancing the model's feature extraction capabilities. Finally, the introduction of a dynamic detection head tackles the issue related to target detection head and attention non-uniformity, thus improving the representation of the target detection head while reducing computational cost. The experimental results demonstrate that the upgraded YOLOv8s-KDT model can rapidly and effectively identify desert grassland plants. Compared to the original model, FLOPs decreased by 50.8%, accuracy improved by 4.5%, and mAP increased by 5.6%. Currently, the YOLOv8s-KDT model is deployed in the mobile plant identification APP of Ningxia desert grassland and the fixed-point ecological information observation platform. It facilitates the investigation of desert grassland vegetation distribution across the entire Ningxia region as well as long-term observation and tracking of plant ecological information in specific areas, such as Dashuikeng, Huangji Field, and Hongsibu in Ningxia.

Fast and practical intrusion detection system based on federated learning for VANET

VANET facilitates communication between vehicles and roadside units, thereby enhancing traffic safety and efficiency. However, it also introduces several attack vectors, compromising security and privacy. To enhance the practicality and precision of existing VANET intrusion detection systems, we propose a novel hybrid algorithm named VAN-IDS. This algorithm combines packet analysis and physical feature analysis. Temporal properties of packets are analyzed using Bi-LSTM, while physical attributes of vehicles are evaluated using LightGBM. Predictive outputs from both models are merged using the Dempster–Shafer theory. Data is collected from the F2MD simulation environment, and experiments are conducted to evaluate the efficacy of VAN-IDS. Results show that VAN-IDS achieves an accuracy exceeding 98.5% in detecting DoS and Sybil attacks, surpassing existing VANET IDSs and meeting real-time detection requirements. Federated learning is introduced, with VAN-FED-IDS designed to accelerate model training and updates, while protecting the privacy of the model and dataset. Roadside units (RSUs) serve as edge computing nodes for local model training, while cloud services aggregate models for collaborative training of detection algorithms. In these experiments, the open-source federated learning frameworks Flower and FedTree are used to assess communication overhead and training duration in both single-machine simulation and multi-machine deployment scenarios. This demonstrates the viability of federated learning, which can protect local data privacy, expedite model training and updates within the IDS, and maintain the original model’s detection accuracy.

Multimodal fall detection for solitary individuals based on audio-video decision fusion processing

Falls often pose significant safety risks to solitary individuals, especially the elderly. Implementing a fast and efficient fall detection system is an effective strategy to address this hidden danger. We propose a multimodal method based on audio and video. On the basis of using non-intrusive equipment, it reduces to a certain extent the false negative situation that the most commonly used video-based methods may face due to insufficient lighting conditions, exceeding the monitoring range, etc. Therefore, in the foreseeable future, methods based on audio and video fusion are expected to become the best solution for fall detection. Specifically, this article outlines the following methodology: the video-based model utilizes YOLOv7-Pose to extract key skeleton joints, which are then fed into a two stream Spatial Temporal Graph Convolutional Network (ST-GCN) for classification. Meanwhile, the audio-based model employs log-scaled mel spectrograms to capture different features, which are processed through the MobileNetV2 architecture for detection. The final decision fusion of the two results is achieved through linear weighting and Dempster-Shafer (D-S) theory. After evaluation, our multimodal fall detection method significantly outperforms the single modality method, especially the evaluation metric sensitivity increased from 81.67% in single video modality to 96.67% (linear weighting) and 97.50% (D-S theory), which emphasizing the effectiveness of integrating video and audio data to achieve more powerful and reliable fall detection in complex and diverse daily life environments.

Gold Nanoparticle-Based Colorimetric and Fluorescent Dual-Mode Lateral Flow Immunoassay for SARS-CoV-2 Detection.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection caused the COVID-19 pandemic, impacting the global economy and medical system due to its fast spread and extremely high infectivity. Efficient control of the spread of the disease relies on a fast, accurate, and convenient detection system for the early screening of the infected population. Although reverse transcription-quantitative polymerase chain reaction (RT-qPCR) is the gold-standard method for SARS-CoV-2 RNA analysis, it has complex experimental procedures and relies on expensive instruments and professional operators. In this work, we proposed a simple, direct, amplification-free lateral flow immunoassay (LFIA) with dual-mode detection of SARS-CoV-2 RNA via direct visualization as well as fluorescence detection. The viral RNA was detected by the designed DNA probes to specifically hybridize with the conserved open reading frame 1ab (ORF1ab), envelope protein (E), and nucleocapsid (N) regions of the SARS-CoV-2 genome to form DNA-RNA hybrids. These hybrids were then recognized by the dual-mode gold nanoparticles (DMNPs) to produce two different readout signals. The fluorescence characteristics of different sizes of GNPs were explored. Under the optimized conditions, the LFIA presented a linear detection range of 104-106 TU/mL with a limit of detection (LOD) of 0.76, 1.83, and 2.58 × 104 TU/mL for lentiviral particles carrying SARS-CoV-2 ORF1ab, E, and N motifs, respectively, in the fluorescent mode, which was up to 10 times more sensitive than the colorimetric mode. Furthermore, the LFIA exhibited excellent specificity to SARS-CoV-2 in comparison with other respiratory viruses. It could be used to detect SARS-CoV-2 in saliva samples. The developed LFIA represents a promising and convenient point-of-care method for dual-mode, rapid detection of SARS-CoV-2, especially in the periods with high infectivity.

Brain tumor detection based on a novel and high-quality prediction of the tumor pixel distributions

The work presented in this paper is in the area of brain tumor detection. We propose a fast detection system with 3D MRI scans of Flair modality. It performs 2 functions, predicting the gray level distribution and location distribution of the pixels in the tumor regions and generating tumor masks with pixel-wise precision. To facilitate 3D data analysis and processing, we introduce a 2D histogram presentation encompassing the gray-level distribution and pixel-location distribution of a 3D object. In the proposed system, specific 2D histograms highlighting tumor-related features are established by exploiting the left-right asymmetry of a brain structure. A modulation function, generated from the input data of each patient case, is applied to the 2D histograms to transform them into coarsely or finely predicted distributions of tumor pixels. The prediction result helps to identify/remove tumor-free slices. The prediction and removal operations are performed to the axial, coronal and sagittal slice series of a brain image, transforming it into a 3D minimum bounding box of its tumor region. The bounding box is utilized to finalize the prediction and generate a 3D tumor mask. The proposed system has been tested extensively with the data of more than 1200 patient cases in BraTS2018∼2021 datasets. The test results demonstrate that the predicted 2D histograms resemble closely the true ones. The system delivers also very good tumor detection results, comparable to those of state-of-the-art CNN systems with mono-modality inputs. They are reproducible and obtained at an extremely low computation cost and without need for training.

Rapid detection of glycosylated hemoglobin levels by a microchip liquid chromatography system in gradient elution mode

BackgroundThe determination of glycosylated hemoglobin (HbA1c) is crucial for diabetes diagnosis and can provide more substantial results than the simple measurement of glycemia. While there is a lack of simple methods for the determination of HbA1c using a point-of-care test (POCT) compared to glycemia measurement. In particular, high-performance liquid chromatography (HPLC) is considered the current gold standard for determining HbA1c levels. However, commercial HPLC systems usually have some sort of disadvantages such as bulky size, high-cost and need for qualified operators. Therefore, there is an urgent demand to develop a portable, and fast HbA1c detection system consuming fewer reagents. ResultsWe present a novel microchip that integrates a micromixer, passive injector, packed column and detection cell. The integrated microchip, in which all the microstructures were formed in the CNC machining center through micro-milling, is small in size (30 mm × 70 mm × 10 mm), and can withstand 1600 psi of liquid pressure. The integrated design is beneficial to reduce the band broadening caused by dead volume. Based on the microchip, a microchip liquid chromatography (LC) system was built and applied to the analysis of HbA1c. The separation conditions of HbA1c in blood calibrator samples were optimized using the microchip LC system. Samples containing four levels of HbA1c were completely separated within 2 min in optimal gradient conditions, with an inaccuracy (<3.2 %), a coefficient of variation (c.v. < 2.1 %) and a correlation coefficient (R2 = 0.993), indicating excellent separation efficiency and reproducibility. SignificanceThe POCT of HbA1c is critical for diabetes diagnosis. The microchip chromatography system was developed for HbA1c determination, which contains an integrated microchip and works under a gradient elution. It surpasses existing chip technology in terms of separation performance and detection speed, providing a competitive advantage for POCT of HbA1c. It is considered one important step for realizing efficient portable systems for timely and accurate diabetes diagnosis.

J48-Based Decision Tree Algorithm in Detecting Kolb’s Learning Style Preferences of Information Technology Students

Teacher education institutions developed interventions to augment both the Teacher’s teaching and the Learner’s learning process. Previous studies focused on detecting learning styles in e-learning using learning management systems and adaptive learning in the online learning process, specifically using the Felder-Silverman learning style model. On the contrary, this study aimed to develop a decision tree-based model to detect the Learner’s learning style inspired by Kolb’s learning style in a face-to-face learning environment. Knowledge discovery in databases through data mining was utilized using the J48 algorithm to develop a decision tree-based model. This study was participated by 408 out of 462 information technology students in a state university in the Philippines. The study’s result was able to develop four J48-based decision trees with conditional rule models for activist, reflector, theorist and pragmatist learners. The evaluation of the decision tree models using confusion matrix and receiver operating curve showed a very high accuracy detection of every learning style (weighted average of 88-96%). This result recommends applying this in an actual system or computer application for easy and fast learning style detection based on the characteristics of the learners.

Simultaneous detection of AFB1 and aflD gene by "Y" shaped aptamer fluorescent biosensor based on double quantum dots.

The developed method for simultaneous detection of aflatoxin B1 (AFB1) and aflD genes can effectively monitor from the source and reduce the safety problems and economic losses caused by the production of aflatoxin, which can be of great significance for food safety regulations. In this paper, we constructed a sensitive and convenient fluorescent biosensor to detect AFB1 and aflD genes simultaneously based on fluorescence resonance energy transfer (FRET) between quantum dots (QDs) and a black hole quenching agent. A stable "Y" shaped aptasensor was employed as the detection platform and a double quantum dot labeled DNA fragment was utilized to be the sensing element in this work. When the targets of AFB1 and aflD genes were presented in the solution, the aptamer in the "Y" shaped probe is specifically recognized by the target. At this time, both Si-carbon quantum dots (Si-CDs) and CdTe QDs are far away from the BHQ1 and BHQ3 to recover the fluorescence. The linear range of the prepared fluorescence simultaneous detection method was as wide as 0.5-500ng·mL-1 with detection lines of 0.64ng·mL-1 for AFB1 and 0.5-500nM with detection lines of 0.75nM for aflD genes (3σ/k). This fabricated fluorescent biosensor was further validated in real rice flour and corn flour samples, which also achieved good results. The recoveries were calculated by comparing the known and found amounts of AFB1 which ranged from 88.4 to approximately 115.32% in the rice flour samples and 90.7 ~ 102.58% in the corn flour samples. The recoveries of aflD genes ranged from 84.32 to approximately 109.3% in the rice flour samples and 89.48 ~ 100.99% in the corn flour samples. Therefore, the proposed biosensor can significantly improve food safety and quality control through a simple, fast, and sensitive agricultural product monitoring and detection system.

Improving the seed detection accuracy of piezoelectric impact sensors for precision seeders. Part II: Evaluation of different plate materials

Precision seeders are crucial in modern agriculture as they directly affect agricultural productivity by ensuring the uniform distribution of seeds in the field. Any non-uniformity in seed distribution can lead to missed or multiple seedings, resulting in potential yield losses. To overcome this issue, researchers have dedicated significant efforts to developing efficient and precise methodologies for assessing and enhancing the seeding performance of precision seeders.Piezoelectric impact sensors are widely used for detecting impacts or collisions and can measure the magnitude and duration of such impacts. This study explores a method to improve the reliability and accuracy of seed detection using piezoelectric signal acquisition and analysis to evaluate the seeding performance of precision seeders. A fast and high-precision piezoelectric detection system was designed and tested using steel, acrylic, medium-density fiberboard (MDF), fiberglass, and autoclaved aerated concrete (AAC) as plate materials. The results demonstrated that fiberglass exhibited the highest measurement accuracy, exceeding 95 %, in detecting soybean, corn, and sunflower seeds at simulated forward speeds of 6 and 12 km/h.The findings of this study contribute to the development of more efficient and accurate methods for testing and detecting the seeding performance of precision seeders. Using fiberglass as a plate material for piezoelectric impact sensors is a promising approach to improving seed detection accuracy and ensuring the quality of seeding operations.

SURG-04. FAST DETECTION OF GLIOMA INFILTRATION USING LABEL-FREE OPTICAL MICROSCOPY AND DEEP NEURAL NETWORKS

Abstract INTRODUCTION Fast and accurate detection of tumor infiltration is a central challenge in the comprehensive management of diffuse glioma patients. Despite our best real-time tumor detection strategies, such as intraoperative MRI and fluorescence-guided surgery, dense and safely resectable tumor infiltration remains at the surgical margin in over 85% of diffuse glioma patients. Patterns of treatment failure demonstrate that glioma recurrence occurs at the surgical margin in the majority of patients due to residual tumor burden. Objective Here, we present FastGlioma, an artificial intelligence (AI)-based intraoperative diagnostic system for fast (&amp;lt; 10 seconds) detection of diffuse glioma infiltration at microscopic resolution without the need for tumor-specific markers. Method FastGlioma is trained using large-scale, self-supervised visual feature learning on stimulated Raman histology (SRH), a rapid, label-free, optical microscopy technique, and a GPT-style whole slide SRH tumor infiltration scoring method. We pushed the performance limits of FastGlioma by investigating the trade-off between imaging speed versus accuracy for microscopic tumor detection. RESULTS In a large prospective external testing cohort of diffuse glioma patients (180 patients, 935 surgical margin specimens) who underwent intraoperative SRH imaging, we demonstrate that FastGlioma was able to detect and quantify microscopic tumor infiltration with an average AUROC of 92.1 +/- 0.0%, performing on par with three expert neuropathologists on the same task. FastGlioma is over 10X faster than previous SRH-based methods and 100X faster than conventional H&amp;E histology. Finally, we demonstrate that FastGlioma was &amp;gt; 20% more accurate at detecting dense tumor infiltration when compared to radiologic features or 5-aminolevulinic fluorescence (98.0% versus 77.8% accuracy) for both IDH-mutant diffuse gliomas and IDH-wildtype glioblastomas. CONCLUSION Our results demonstrate how intraoperative optical imaging and deep neural networks can achieve fast and accurate tumor detection, unlocking the role of AI in improving the surgical management of brain tumor patients.

Three-Dimensional Structure Measurement for Potted Plant Based on Millimeter-Wave Radar

Potted plant canopy extraction requires a fast, accurate, stable, and affordable detection system for precise pesticide application. In this study, we propose a new method for extracting three-dimensional canopy information of potted plants using millimeter-wave radar and evaluate the system on plants in static, rotating, and rotating-while-spraying states. The position and rotation speed of the rotating platform are used to compute the rotation–translation matrix between point clouds, enabling the multi-view point clouds to be overlaid on the world coordinate system. Point cloud extraction is performed by applying the Density-Based Spatial Clustering of Applications with Noise algorithm (DBSCAN), while an Alpha-shape algorithm is used for three-dimensional reconstruction of the canopy. Our measurement results for the 3D reconstruction of plants at different growth stages showed that the reconstruction model has higher accuracy under the rotation condition than that under the static condition, with average relative errors of 41.61% and 10.21%, respectively. The significant correlation between the sampling data with and without spray reached 0.03, indicating that the effect of the droplets on radar detection during the spray process can be neglected. This study provides guidance for plant canopy detection using millimeter-wave radar for advanced agricultural informatization and automation.

Wi-Flex

In this paper, we are interested in startle reflex detection with WiFi signals. We propose that two parameters related to the received signal bandwidth, maximum normalized bandwidth and bandwidth-intense duration, can successfully detect reflexes and robustly differentiate them from non-reflex events, even from those that involve intense body motions (e.g., certain exercises). In order to confirm this, we need a massive RF reflex dataset which would be prohibitively laborious to collect. On the other hand, there are many available reflex/non-reflex videos online. We then propose an efficient way of translating the content of a video to the bandwidth of the corresponding received RF signal that would have been measured if there was a link near the event in the video, by drawing analogies between our problem and the classic bandwidth modeling work of J. Carson in the context of analog FM radios (Carson's Rule). This then allows us to translate online reflex/non-reflex videos to an instant large RF bandwidth dataset, and characterize optimum 2D reflex/non-reflex decision regions accordingly, to be used during real operation with WiFi. We extensively test our approach with 203 reflex events, 322 non-reflex events (including 142 intense body motion events), over four areas (including several through-wall ones), and with 15 participants, achieving a correct reflex detection rate of 90.15% and a false alarm rate of 2.49% (all events are natural). While the paper is extensively tested with startle reflexes, it is also applicable to sport-type reflexes, and is thus tested with sport-related reflexes as well. We further show reflex detection with multiple people simultaneously engaged in a series of activities. Optimality of the proposed design is also demonstrated experimentally. Finally, we conduct experiments to show the potential of our approach for providing cost-effective and quantifiable metrics in sports, by quantifying a goalkeeper's reaction. Overall, our results confirm a fast, robust, and cost-effective reflex detection system, without collecting any RF training data, or training a neural network.

Rapid appearance quality of rice based on machine vision and convolutional neural network research on automatic detection system.

In the process of rice production and storage, there are many defects in the traditional detection methods of rice appearance quality, but using modern high-precision instruments to detect the appearance quality of rice has gradually developed into a new research trend at home and abroad with the development of agricultural artificial intelligence. In this study, we independently designed a fast automatic rice appearance quality detection system based on machine vision technology by introducing convolutional neural network and image processing technology. In this study, NIR and RGB images were generated into five-channel image data by superposition function, and image are preprocessed by combining the Watershed algorithm with the Otus adaptive threshold function. Different grains in the samples were labeled and put in the convolutional neural network for training. The rice grains were classified and the phenotype data were analyzed by selecting the optimal training model to realize the detection of rice appearance quality. The experimental results showed that the resolution of the system could reach 92.3%. In the detection process, the system designed with this method not only reduces the subjectivity problems caused by different detection environments, visual fatigue caused large sample size and the inspector's personal factors, but also significantly improves the detection time and accuracy, which further enhances the detection efficiency of rice appearance quality, and has positive significance for the development of the rice industry.