Devices For Real-time Detection Research Articles

EcoDetect-YOLO: A Lightweight, High-Generalization Methodology for Real-Time Detection of Domestic Waste Exposure in Intricate Environmental Landscapes.

In response to the challenges of accurate identification and localization of garbage in intricate urban street environments, this paper proposes EcoDetect-YOLO, a garbage exposure detection algorithm based on the YOLOv5s framework, utilizing an intricate environment waste exposure detection dataset constructed in this study. Initially, a convolutional block attention module (CBAM) is integrated between the second level of the feature pyramid etwork (P2) and the third level of the feature pyramid network (P3) layers to optimize the extraction of relevant garbage features while mitigating background noise. Subsequently, a P2 small-target detection head enhances the model's efficacy in identifying small garbage targets. Lastly, a bidirectional feature pyramid network (BiFPN) is introduced to strengthen the model's capability for deep feature fusion. Experimental results demonstrate EcoDetect-YOLO's adaptability to urban environments and its superior small-target detection capabilities, effectively recognizing nine types of garbage, such as paper and plastic trash. Compared to the baseline YOLOv5s model, EcoDetect-YOLO achieved a 4.7% increase in mAP0.5, reaching 58.1%, with a compact model size of 15.7 MB and an FPS of 39.36. Notably, even in the presence of strong noise, the model maintained a mAP0.5 exceeding 50%, underscoring its robustness. In summary, EcoDetect-YOLO, as proposed in this paper, boasts high precision, efficiency, and compactness, rendering it suitable for deployment on mobile devices for real-time detection and management of urban garbage exposure, thereby advancing urban automation governance and digital economic development.

PMT Fluorescence Signal Denoising Processing Based on Wavelet Transform and BP Neural Network

Air is the environmental foundation for human life and production, and its composition changes are closely related to human activities. Sulfur dioxide (SO2) is one of the main atmospheric pollutants, mainly derived from the combustion of fossil fuels. But SO2 is a trace gas in the atmosphere, and its concentration may be less than one part per billion (ppb). This paper is based on the principle of photoluminescence and uses a photomultiplier tube (PMT) as a photoelectric converter to develop a device for real-time detection of SO2 concentration in the atmosphere. This paper focuses on the impact of noise interference on weak electrical signals and uses wavelet transform to denoise the signals. At the same time, considering that the photoelectric system is susceptible to temperature changes, a multi parameter fitting model is constructed, and a BP neural network is used to further process the signal, separating the real data from the original data. Finally, a high-precision and wide-range trace level sulfur dioxide concentration detection device and algorithm were obtained.

A Nanoporous Polymer Modified with Hexafluoroisopropanol to Detect Dimethyl Methylphosphonate.

The increasing threat of nerve agents has prompted the need for gas sensors with fast response, high sensitivity, and good stability. In this work, the hexafluoroisopropanol functional group was modified on a porous aromatic framework material, which served as a sensitive material for detecting dimethyl methylphosphonate. A nerve agent sensor was made by coating sensitive materials on a surface acoustic wave device. Lots of pores in sensitive materials effectively increase the specific surface area and provide channels for diffusion of gas molecules. The introduction of hexafluoroisopropanols enables the sensor to specifically adsorb dimethyl methylphosphonate and improves the selectivity of the sensor. As a result, the developed gas sensor was able to detect dimethyl methylphosphonate at 0.8 ppm with response/recovery times of 29.8/43.8 s, and the detection limit of the gas sensor is about 0.11 ppm. The effects of temperature and humidity on the sensor were studied. The results show that the baseline of the sensor has a linear relationship with temperature and humidity, and the temperature and humidity have a significant effect on the response of the sensor. Furthermore, a device for real-time detection of nerve agent is reported. This work provides a new strategy for developing a gas sensor for detecting nerve agents.

A H2O2 generation-detection-regulation integrated platform for boosting the efficiency of peroxygenase-catalysed C–H oxidative hydroxylation

The peroxygenases are ideal biocatalysts for the selective oxyfunctionalisation of stable C–H bonds. However, the catalytic efficiency of this approach is limited due to enzyme lability toward oxidant H2O2. Although the reported in-situ H2O2 generation system enables the stable biocatalytic process without deactivating the enzyme, the greatest catalytic potential of peroxygenases still cannot be fulfilled effectively. To address the above issue, a H2O2 generation-detection-regulation platform that integrated an effective organocatalyst-driven H2O2 generation system, a precise electrochemical H2O2 real-time detection device, and a convenient H2O2 regulation strategy was first developed. The suitable range of H2O2 generation rate for maximizing the catalytic efficiency of peroxygenases while minimizing inactivation of the enzyme was firstly obtained by simply adjusting the amount of organocatalyst. According to the determined suitable range, the C–H oxyfunctionalisation efficiency of peroxygenases for each substrate was significantly boosted, achieving ∼3-fold of the reported highest turnover frequency.

Real-time marine target recognition method of underwater inspection robot based on computer vision

In the complex marine environment, target recognition is difficult, and the real-time detection has a slow speed. In this article, a target recognition method combining underwater generative adversarial network and improved YOLOv4 is proposed, which is named M-YOLOv4. Firstly, the images collected by the underwater inspection robot are enhanced using the underwater generative adversarial network algorithm to obtain the training datasets. Secondly, the YOLOv4 target detection algorithm combines the feature extraction network of MoblieNetv3 for lightweight processing, which reduces the network model size, and reduces the number of algorithm calculations and parameters. Then, change the size of the spatial pyramid pooling module pooling kernel, which can enlarge receptive field and integrate characteristics of different receptive fields. Finally, the processed datasets are transferred to the improved M-YOLOv4 algorithm for training, and the trained model is transplanted to the Jetson Nano hardware device for real-time detection. The results of experiments show that the mean average precision value of the improved M-YOLOv4 recognition is 90.77%, which is 2.02% higher than that of the unimproved one. The frame per second value of the lightweight YOLOv4 algorithm with MobileNetv3 is 27, an increase of 12 compared with YOLOv4. The improved M-YOLOv4 algorithm can perform accurate detection of marine multi-targets on embedded devices.

Development of an electrochemical DNA-based biosensor for the detection of the cardiovascular pharmacogenetic-altering SNP CYP2C9*3

Cardiovascular diseases are among the major causes of mortality and morbidity. Warfarin is often prescribed for these disorders, an anticoagulant with inter and intra-dosage variability dose required to achieve the target international normalized ratio. Warfarin presents a narrow therapeutic index, and due to its variability, it can often be associated with the risk of hemorrhage, or in other patients, thromboembolism. Single-nucleotide polymorphisms are included in the causes that contribute to this variability. The Cytochrome P450 (CYP) 2C9*3 genetic polymorphism modifies its enzymatic activity, and hence warfarin's plasmatic concentration. Thus, the need for a selective, rapid, low-cost, and real-time detection device is crucial before prescribing warfarin. In this work, a disposable electrochemical DNA-based biosensor capable of detecting CYP2C9*3 polymorphism was developed. By analyzing genomic databases, two specific 78 base pairs DNA probes; one with the wild-type adenine (Target-A) and another with the cytosine (Target-C) single-nucleotide genetic variation were designed. The biosensor implied the immobilization on screen-printed gold electrodes of a self-assembled monolayer composed by mercaptohexanol and a linear CYP2C9*3 DNA-capture probe. To improve the selectivity and avoid secondary structures a sandwich format of the CYP2C9*3 allele was designed using complementary fluorescein isothiocyanate-labeled signaling DNA probe and enzymatic amplification of the electrochemical signal. Chronoamperometric measurements were performed at a range of 0.015–1.00 nM for both DNA targets achieving limit of detection of 42 p.m. The developed DNA-based biosensor was able to discriminate between the two synthetic target DNA targets, as well as the targeted denatured genomic DNA, extracted from volunteers genotyped as non-variant homozygous (A/A) and heterozygous (A/C) of the CYP2C9*3 polymorphism.

Thermal inspection of photovoltaic modules with deep convolutional neural networks on edge devices in AUV

Solar photovoltaic (PV), a green energy harvesting system, is growing worldwide rapidly. It is a friendly environmental energy system. During operation, anomalies could appear in the PV modules, which reduce energy harvesting efficiency, shorten the lifetime and lead to an increase in the amount of heavy metals being released into the environment. In this research, a remote sensing method is proposed for the fast and efficient detection of anomalies in photovoltaic (PV) systems. An infrared radiation (IR) camera mounted on flying vehicles (e.g., drone) to capture IR images of solar panels. Then, convolutional neural networks (CNN) are developed to detect abnormal cells in the PV systems. The CNN model are then quantized and implemented on edge devices for real-time detection of anomalies. We evaluated these models on 11 types of anomalies in PV modules collected from 826 solar panels worldwide. Moreover, the classification decision of each layer of the CNN model can be visualized by the Gradient-weighted Class Activation Mapping method to reinforce the classification output. In addition, we implemented the models on an edge device (Jetson Nano) to evaluate real-time inspection capabilities. The proposed model is efficient compared to the other previous models, which takes only 1.04 ms to progress one image on average while still yields a high accuracy of 85.35% when running on the Jetson Nano board.

Development and Validation of a Low-Cost Device for Real-Time Detection of Fatigue Damage of Structures Subjected to Vibrations.

This paper presents the development and validation of a low-cost device for real-time detection of fatigue damage of structures subjected to vibrations. The device consists of an hardware and signal processing algorithm to detect and monitor variations in the structural response due to damage accumulation. The effectiveness of the device is demonstrated through experimental validation on a simple Y-shaped specimen subjected to fatigue loading. The results show that the device can accurately detect structural damage and provide real-time feedback on the health status of the structure. The low-cost and easy-to-implement nature of the device makes it promising for use in structural health monitoring applications in various industrial sectors.

A Bluetooth-Enabled Device for Real-Time Detection of Sitting, Standing, and Walking: Cross-Sectional Validation Study.

This study assesses the accuracy of a Bluetooth-enabled prototype activity tracker called the Sedentary behaviOR Detector (SORD) device in identifying sedentary, standing, and walking behaviors in a group of adult participants. The primary objective of this study was to determine the criterion and convergent validity of SORD against direct observation and activPAL. A total of 15 healthy adults wore SORD and activPAL devices on their thighs while engaging in activities (lying, reclining, sitting, standing, and walking). Direct observation was facilitated with cameras. Algorithms were developed using the Python programming language. The Bland-Altman method was used to assess the level of agreement. Overall, 1 model generated a low level of bias and high precision for SORD. In this model, accuracy, sensitivity, and specificity were all above 0.95 for detecting sitting, reclining, standing, and walking. Bland-Altman results showed that mean biases between SORD and direct observation were 0.3% for sitting and reclining (limits of agreement [LoA]=-0.3% to 0.9%), 1.19% for standing (LoA=-1.5% to 3.42%), and -4.71% for walking (LoA=-9.26% to -0.16%). The mean biases between SORD and activPAL were -3.45% for sitting and reclining (LoA=-11.59% to 4.68%), 7.45% for standing (LoA=-5.04% to 19.95%), and -5.40% for walking (LoA=-11.44% to 0.64%). Results suggest that SORD is a valid device for detecting sitting, standing, and walking, which was demonstrated by excellent accuracy compared to direct observation. SORD offers promise for future inclusion in theory-based, real-time, and adaptive interventions to encourage physical activity and reduce sedentary behavior.

Zinc-Air Battery-Based Self-Powered Sensor with High Output Power for Ultrasensitive MicroRNA let-7a Detection in Cancer Cells.

Self-powered sensors do not require a power supply and are easy to miniaturize, which have potential for constructing wearable, portable, and real-time detection devices. However, it is challenging for the detection of low abundant targets due to the low output power density of fuel cells and much interference of complex biological environment. Herein, a new kind of photocatalytic zinc-air battery-based self-powered electrochemical sensor (ZAB-SPES) was constructed for the detection of microRNA let-7a (miRNA let-7a) by combining magnetic nanobeads (MBs) with a metal-organic framework loaded with glucose oxidase (MOFs@GOX). Poly(1,4-di(2-thienyl))benzene (PDTB) was used as the photocathode material, and the proposed ZAB-SPES had a high power density of 22.8 μW/cm2, which was 2-3-fold of commonly used photofuel cells. MBs can capture and separate miRNA from complex samples quickly with a high separation efficiency of 99% within 60 s. The competitive reaction of oxygen reduction reaction between PDTB and MOFs@GOX would change the output power density of the ZAB-SPES. Based on the relationship between output power density and target concentration, the ZAB-SPES realized ultrasensitive detection of miRNA let-7a with a detection limit down to 1.38 fM. Furthermore, the successful detection of miRNA let-7a in A549 cancer cells indicated the great prospects of ZAB-SPES in clinical analysis and early diagnosis of cancers.

SOMN_IA: Portable and Universal Device for Real-Time Detection of Driver’s Drowsiness and Distraction Levels

In this paper, we propose a portable device named SOMN_IA, to detect drowsiness and distraction in drivers. The SOMN_IA can be installed inside of any type of vehicle, and it operates in real time, alerting the dangerous state caused by drowsiness and/or distraction in the driver. The SOMN_IA contains three types of alarm: light alarm, sound alarm, and the transmission of information about the driver’s dangerous state to a third party if the driver does not correct his/her dangerous state. The SOMN_IA contains a face detector and a classifier based on the convolutional neural networks (CNN), and it aids in the management of consecutive information, including isolated error correction mechanisms. All of the algorithmic parts of the SOMN_IA are analyzed and adjusted to operate in real-time in a portable device with limited computational power and memory space. The SOMN_IA requires only a buck-type converter to connect to the car battery. The SONM_IA discriminates correctly between real drowsiness and normal blinking, as well as between real dangerous distraction and a driver’s normal attention to his/her right and left. Although the real performance of the SOMN_IA is superior to the CNN classification accuracy thanks to isolated error correction, we compare the CNN classification accuracy with the previous systems.

A Real-Time Detection Device for the Rapid Quantification of Skin Casual Sebum Using the Oil Red O Staining Method.

The human skin sebum suggests that it (along with other epidermal surface lipids) plays a role in skin barrier formation, the moderation of cutaneous inflammation, and antimicrobial defense. Various methods have been developed for collecting and measuring skin sebum. We tested methods of detection using “color intensity”, by staining the skin casual sebum. This process was conducted in three steps; first, the selection of materials for sebum collection; second, staining the collected sebum; third, the development of a device that can measure the level of stained sebum. A plastic film was used to effectively collect sebum that increased with the replacement time of the sebum. In addition, the collected sebum was stained with Oil Red O (ORO) and checked with RGB; as a result, the R2 value was higher than 0.9. It was also confirmed that the correlation value was higher than 0.9 in the comparison result with Sebumeter®, which is a common standard technology. Finally, it was confirmed that the R2 value was higher than 0.9 in the detection value using the sensor. In conclusion, we have proven the proof of concept (PoC) for this method, and we would like to introduce an effective sebum measurement method that differs from the existing method.

A fully integrated fast scan cyclic voltammetry electrochemical method: Improvements in reaction kinetics and signal stability for specific Ag(I) and Hg(II) analysis

• A fully integrated FSCV electrochemical method is developed. • This proposed method is to improve reaction kinetics and signal stability. • TdT-yielded DNAs can be used to construct electrode substrate favorably. • The platform is suited for Ag(I) and Hg(II) analysis well. • The method is conducive to the development of the real-time detection device. Inspired by the urgent need to detect trace heavy metal ions in various real samples, we construct a unique electrochemical biosensing method for heavy metal ions Ag(I) and Hg(II) analysis in this work. The biosensor is constructed by using terminal deoxynucleotidyl transferase (TdT) to catalyze the addition of dCTP and dTTP in 3′-OH end of original DNAs, thus producing enough long DNAs. This unique DNAs have a strong affinity to Ag(I) and Hg(II), and C-Ag(I)-C and T-Hg(II)-T structures occurs at the electrode surface. Meanwhile, the introduction of fast-scanning cyclic voltammetry (FSCV) can achieve the stable signal output all the while, where the reaction kinetics are superior to the diffusion kinetics, resulting in a significant improvement on reaction kinetics and signal stability. Based on it, simple detection of Ag(I) or Hg(II) is demonstrated powerfully with good detection limit (3 × 10 −14 M or 3 × 10 −15 M, S/N = 3); additionally, simultaneous detection of Ag(I) and Hg(II) is achieved with negligible interference. Furthermore, the proposed method has been also applied for some DNA electronic computing logic gates by designing simple or multiple inputs and output favorably. Based on these, the FSCV method has potential applications for the monitoring of heavy metal ions in real sample analysis.

A real-time detection device for the rapid quantification of skin casual sebum using the Oil Red O staining method

A real-time detection device for the rapid quantification of skin casual sebum using the Oil Red O staining method

A real-time detection device for the rapid quantification of skin casual sebum using the Oil Red O staining method

A real-time detection device for the rapid quantification of skin casual sebum using the Oil Red O staining method

A real-time detection device for the rapid quantification of skin casual sebum using the Oil Red O staining method

A real-time detection device for the rapid quantification of skin casual sebum using the Oil Red O staining method

A Fully Integrated and Handheld Electrochemiluminescence Device for Real-Time Detection of Dopamine in Bio-Samples

A Fully Integrated and Handheld Electrochemiluminescence Device for Real-Time Detection of Dopamine in Bio-Samples

Smartphone based microfluidic lab-on-chip device for real-time detection, counting and sizing of living algae

A smartphone integrated microfluidic lab-on-chip device was developed for the real-time detection, counting and sizing of living algae in simulated ballast water samples. The device consists of a microfluidic chip, a customer-made fluorescence imaging platform and a smartphone. When living algae pass the laser illumination region of the microfluidic chip, chlorophyll fluorescence is emitted and shown in the smartphone. An algorithm in the smartphone detects, counts and sizes the detected living algae. As a proof of concept, two different sizes of algae were tested and a detection accuracy of larger than 92% was achieved. The sizing accuracy is 94%. The largest moving velocity allowed for detection is determined by the diameter of the algae and the frame per second (fps) of the smartphone. The device is simple in structure and operation and suitable for on-site evaluating the living status of algae in treated ship’s ballast water.

Portable and Autonomous Device for Real-time Colorimetric Detection: Validation for Phosphorous and Nitrite Detection

Application of autonomous devices has disrupted routine digital monitoring in all the domains specifically in the fields of environmental monitoring, agriculture and allied sector, health care, and medical diagnostics. These modern autonomous field-deployable devices facilitate reliable testing, data acquisition, and efficient and immediate data transmission. Among various popular detection methods, colorimetric detection method is capable of detecting environmental samples with very low concentration with a high level of precision, are cost-effective, and provide ease-of-use. Hence, in this work, a portable, and autonomous device for real-time detection was designed using commercially available light-emitting diode (LED) and a photodiode, having peak response at a wavelength at which the chromophore exhibits absorption, were used to build the colorimetric detection device. The developed device is a portable, highly sensitive, low-cost, and low-power-consuming colorimetric detection platform integrated with Internet of Things (IoT) and Bluetooth modules for online and offline data transmission, respectively. The device functionality was further enhanced by adding other important attributes such as data storage, retrieval, and real-time monitoring capabilities. For the proof-of-concept, phosphate and nitrite samples were tested colorimetrically. Phosphorous was detected in the linear range of 10–100 μM with the limit of detection (LOD) being 0.074 ppm, while nitrite was detected in a linear range of 5–30 μM with LOD of 0.06 ppm. By suitably modifying the optoelectronic components, the developed colorimetric detection platform can be made potentially amenable to sense a variety of analytes.

Multi-task deep learning for cardiac rhythm detection in wearable devices

Wearable devices enable theoretically continuous, longitudinal monitoring of physiological measurements such as step count, energy expenditure, and heart rate. Although the classification of abnormal cardiac rhythms such as atrial fibrillation from wearable devices has great potential, commercial algorithms remain proprietary and tend to focus on heart rate variability derived from green spectrum LED sensors placed on the wrist, where noise remains an unsolved problem. Here we develop DeepBeat, a multitask deep learning method to jointly assess signal quality and arrhythmia event detection in wearable photoplethysmography devices for real-time detection of atrial fibrillation. The model is trained on approximately one million simulated unlabeled physiological signals and fine-tuned on a curated dataset of over 500 K labeled signals from over 100 individuals from 3 different wearable devices. We demonstrate that, in comparison with a single-task model, our architecture using unsupervised transfer learning through convolutional denoising autoencoders dramatically improves the performance of atrial fibrillation detection from a F1 score of 0.54 to 0.96. We also include in our evaluation a prospectively derived replication cohort of ambulatory participants where the algorithm performed with high sensitivity (0.98), specificity (0.99), and F1 score (0.93). We show that two-stage training can help address the unbalanced data problem common to biomedical applications, where large-scale well-annotated datasets are hard to generate due to the expense of manual annotation, data acquisition, and participant privacy.