ENVIRONMENTAL POLLUTION
·
2019
·
IF 5.714
Hui Huang,Chao Wang,Shuchang Liu,Zehao Sun,Dejun Zhang,Caicai Liu,Yang Jiang,Shuyue Zhan,Haofei Zhang,Ren Xu
The automatic identification (location, segmentation , and classification) by UAV- based optical imaging of spills of transparent floating Hazardous and Noxious Substances (HNS) benefits the on-site response to spill incidents, but it is also challenging. With a focus on the on-site optical imaging of HNS, this study explores the potential of single spectral imaging for HNS identification using the Faster R-CNN architecture. Images at 365 nm (narrow UV band), blue channel images (visible broadband of ∼400–600 nm), and RGB images of typical HNS (benzene, xylene, and palm oil) in different scenarios were studied with and without Faster R-CNN. Faster R-CNN was applied to locate and classify the HNS spills. The segmentation using Faster R-CNN-based methods and the original masking methods, including Otsu, Max entropy, and the local fuzzy thresholding method (LFTM), were investigated to explore the optimal wavelength and corresponding image processing method for the optical imaging of HNS. We also compared the classification and segmentation results of this study with our previously published studies on multispectral and whole spectral images. The results demonstrated that single spectral UV imaging at 365 nm combined with Faster R-CNN has great potential for the automatic identification of transparent HNS floating on the surface of the water. RGB images and images using Faster R-CNN in the blue channel are capable of HNS segmentation.
研究领域:
环境科学
·
图像处理
·
遥感技术
✓ 已验证
产品关联
DOI
PubMed
高影响因子
Separations
·
2025
·Vol. 12
·期 2
·22
·
IF 2.7
Huan-Huan Fan,Xiang-Ling Wang,Jie Feng,Wen-Ying Li
A comprehensive understanding of the compositions and physicochemical properties of coal-based liquids is conducive to the rapid development of multipurpose, high-performance, and high-value functional chemicals. However, because of their complex compositions, coal-based liquids generate two-dimensional gas chromatography (GC × GC) chromatograms that are very complex and very time consuming to analyze. Therefore, the development of a method for accurately and rapidly analyzing chromatograms is crucial for understanding the chemical compositions and structures of coal-based liquids, such as direct coal liquefaction (DCL) oils and coal tar. In this study, DCL oils were distilled and qualitatively analyzed using GC × GC chromatograms. A deep-learning (DL) model was used to identify spectral features in GC × GC chromatograms and predominantly categorize the corresponding DCL oils as aliphatic alkanes, cycloalkanes, mono-, bi-, tri-, and tetracyclic aromatics. Regional labels associated with areas in the GC × GC chromatograms were fed into the mask-region-based convolutional neural network’s (Mask R-CNN’s) algorithm. The Mask R-CNN accurately and rapidly segmented the GC × GC chromatograms into regions representing different compounds, thereby automatically qualitatively classifying the compounds according to their spots in the chromatograms. Results show that the Mask R-CNN model’s accuracy, precision, recall, F1 value, and Intersection over Union (IoU) value were 93.71%, 96.99%, 96.27%, 0.95, and 0.93, respectively. DL is effective for visually comparing GC × GC chromatograms to analyze the compositions of chemical mixtures, accelerating GC × GC chromatogram interpretation and compound characterization and facilitating comparisons of the chemical compositions of multiple coal-based liquids produced in the coal and petroleum industry. Applying DL to analyze chromatograms improves analysis efficiency and provides a new method for analyzing GC × GC chromatograms, which is important for fast and accurate analysis.
研究领域:
化学工程
·
人工智能
·
能源科学
✓ 已验证
产品关联
DOI
高影响因子
Chemistry-An Asian Journal
·
2013
·Vol. 8
·期 7
·1504-1513
·
IF 4.572
Si-Hai Wu,Yu-Wu Zhong,Jiannian Yao
Graphical NN-CNN breaking news : 2,3-Di(2-pyridyl)-5-phenylpyrazine, which is able to bind two metals through a NN-CNN-type coordination mode, has been designed and synthesized. A RuPt heterobimetallic complex with this bridging ligand shows near-infrared emission at 750 nm, with a quantum yield of 0.41 % and an excited-state lifetime of 170 ns. en This link goes to a English section zh This link goes to a English section A new bridging ligand, 2,3-di(2-pyridyl)-5-phenylpyrazine (dpppzH), has been synthesized. This ligand was designed so that it could bind two metals through a NN-CNN-type coordination mode. The reaction of dpppzH with cis -[(bpy) 2 RuCl 2 ] (bpy=2,2′-bipyridine) affords monoruthenium complex [(bpy) 2 Ru(dpppzH)] 2+ ( 12+ ) in 64 % yield, in which dpppzH behaves as a NN bidentate ligand. The asymmetric biruthenium complex [(bpy) 2 Ru(dpppz)Ru(Mebip)] 3+ ( 23+ ) was prepared from complex 12+ and [(Mebip)RuCl 3 ] (Mebip=bis( N -methylbenzimidazolyl)pyridine), in which one hydrogen atom on the phenyl ring of dpppzH is lost and the bridging ligand binds to the second ruthenium atom in a CNN tridentate fashion. In addition, the RuPt heterobimetallic complex [(bpy) 2 Ru(dpppz)Pt(CCPh)] 2+ ( 42+ ) has been prepared from complex 12+ , in which the bridging ligand binds to the platinum atom through a CNN binding mode. The electronic properties of these complexes have been probed by using electrochemical and spectroscopic techniques and studied by theoretical calculations. Complex 12+ is emissive at room temperature, with an emission λ max =695 nm. No emission was detected for complex 23+ at room temperature in MeCN, whereas complex 42+ displayed an emission at about 750 nm. The emission properties of these complexes are compared to those of previously reported Ru and RuPt bimetallic complexes with a related ligand, 2,3-di(2-pyridyl)-5,6-diphenylpyrazine. en This link goes to a English section zh This link goes to a English section 1
研究领域:
配位化学
·
无机化学
✓ 已验证
DOI
PubMed
高影响因子
CHEMICAL ENGINEERING JOURNAL
·
2024
·
IF 13.3
Yugui Cheng,Simian Fu,Kaiming Jin,Yiying Liu,Jingtong Ma,Deliang Li,Qingying Lyu,Yehan Li,Xiaoyang Jiang,Ruonan Liu,Ye Tian
Hydrogels displaying both high toughness and flexibility hold substantial practical value. However, it has been challenging to achieve these properties simultaneously. To address this challenge, we developed a special structure hydrogel named PAB-S inspired by chrysalis shell. Astragalus polysaccharide (AP) was copolymerized with polyvinyl alcohol (PVA) and betaine hydrochloride (BH) to prepare a low-modulus hydrogel, PAB. Subsequently, surface modification of the PAB hydrogel using sodium phytate (SP) resulted in the formation of the “shell” structured PAB-S hydrogel. The fracture strength of the shell-structured hydrogel increased by about 0.8 MPa. Meanwhile, PAB-S had a maximum tensile strain of 418 %, a toughness of 6.82 MJ/m 3 , and a modulus of elasticity of approximately 0.6 MPa. In addition, PAB-S hydrogel offers high strain sensitivity (GF up to 4.7), ultra-low response time of 20 ms. Finally, leveraging 2.4G communication technology and a deep learning (1D-CNN) algorithm, advanced functionalities such as wireless remote intelligent control, and deep learning-based finger grip disorder identification were realized using the PAB-S hydrogel sensor. The PAB-S hydrogel sensor holds promising prospects for applications in fields including deep learning, intelligent sensing, medical rehabilitation, and human–machine synchronization.
研究领域:
材料科学
·
生物医学工程
·
传感器技术
✓ 已验证
产品关联
DOI
高影响因子
Remote Sensing
·
2023
·Vol. 16
·期 1
·
IF 5
Menghua Li,Hanfei Wu,Mengshi Yang,Cheng Huang,Bo-Hui Tang
Multi-temporal Interferometric Synthetic Aperture Radar technique (MTInSAR) has emerged as a valuable tool for measuring ground motion in a wide area. However, interpreting displacement time series and identifying dangerous signals from millions of InSAR coherent targets is challenging. In this study, we propose a method combining stacked autoencoder (SAE) and convolutional neural network (CNN) to classify InSAR time series and ease the interpretation of movements. The InSAR time series are classified into five categories, including stable, linear, accelerating, deceleration, and phase unwrapping error (PUE). The accuracy of labeled samples reaches 95.1%, reflecting the performance of the proposed method. This method was applied to the InSAR results for Kunming extracted from 171 ascending Sentinel-1 images from January 2017 to September 2022. The classification map of the InSAR time series shows that stable coherent points dominate around 79.28% of the area, with linear patterns at 10.70%, decelerating at 5.30%, accelerating at 4.72%, and PUE patterns at 3.60%. The results demonstrate that this method can distinguish different ground motion features and detect nonlinear deformation signals on a large scale without human intervention.
✓ 已验证
DOI
高影响因子
JOURNAL OF FOOD ENGINEERING
·
2023
·
IF 5.5
Ya Liu,Yueying Zhang,Feiwu Long,Jinrong Bai,Yina Huang,Hong Gao
The accumulation of lipid oxidation and biogenic amines is the primary cause of pork sausage spoilage during storage. Therefore, this study aimed to develop a colorimetric microfluidic paper analytical device (μPAD) that specifically responded to these two factors to evaluate sausage spoilage during storage. A dataset consisting of 4096 images of μPADs was collected, and a convolutional neural networks (CNN)-based classification model (Resnet50) was trained and tested with an accuracy, F1 score, and recall rate of 97.10%, 97.14%, and 99.17%, respectively. Additionally, the CNN-based model was integrated into a smartphone application with user-friendly interfaces catering to both professional and non-professional users. Furthermore, the classification method was validated by predicting the shelf life of sausages stored at different temperatures. Compared to conventional methods, this approach provided a cost-effective, rapid, and portable detection method for assessing pork sausage freshness while broadening the application of smartphone-based colorimetric μPADs in food safety and quality control.
研究领域:
食品科学
·
人工智能
·
分析化学
✓ 已验证
产品关联
DOI
高影响因子
JOURNAL OF AGRICULTURAL AND FOOD CHEMISTRY
·
2025
·
IF 6.2
Shenye Qu,Yihang Liu,Jietao Liu,Xiaohu Wu,Pengfei Li,Qing Yu,Gaoxue Wang,Fei Ling
Aquaculture is a rapidly growing sector of global food production, playing a vital role in poverty alleviation, food security, and income generation. However, it faces substantial challenges, particularly due to infections caused by the protozoan Ichthyophthirius multifiliis, leading to reduced yields and economic losses. In this study, two classes of magnolol derivatives (M1–M26) were synthesized and evaluated for their parasiticidal activity against I. multifiliis theronts and tomonts. Based on the determined EC50 values, two significant convolutional neural networks (CNNs) and pharmacophore models were developed, guiding the design and synthesis of three new compounds. Among these, compound new-1 exhibited superior parasiticidal efficacy both in vitro and in vivo compared to magnolol and the commercial parasiticide methylene blue, with EC50 values of 0.197 and 0.252 mg/L, respectively. Toxicity assays demonstrated that compound new-1 showed no significant harmful effects on goldfish and zebrafish embryos at effective concentrations. Further, in silico and experimental analyses identified CDK2 as a molecular target for compound new-1, which disrupted the reproduction and exerts parasiticidal activity against I. multifiliis. Additionally, compound new-1 exhibited antifungal activity against Aspergillus flavus with a MIC of ∼0.8 mg/mL, suggesting its potential application in food preservation. This study provides valuable insights into the development of magnolol-based agents for aquaculture.
研究领域:
水产养殖
·
药物化学
·
计算生物学
·
分子生物学
✓ 已验证
DOI
PubMed
高影响因子
FOOD CONTROL
·
2025
·
IF 6.3
Jing He,Zhipeng Ouyang,Changfan Zhang,Danfei Liu
Traditional food expiration labels cannot reflect the real-time freshness status of meat products, leading to food safety risks and economic losses. This study proposes a chicken freshness detection method that integrates intelligent indicator films with an improved convolutional neural network (ESD-YOLOv8). The indicator film design employs UiO-66 and UiO-66-Br metal–organic frameworks (MOFs) as carriers, combined with natural anthocyanins and chitosan-PVA (CS-PVA) biodegradable matrix. The network architecture introduces three key modules: (1) Deformable Attention Enhanced Bottleneck (DAEB) module with deformable attention mechanisms to adaptively adjust receptive fields for precise color gradient detection; (2) Spatial Grouped Attention Fusion Pyramid Module (SGAFPM); (3) Optimized detection head for improved recognition accuracy. This method provides a non-invasive, rapid, and low-cost technical solution for food safety monitoring.
研究领域:
食品安全
·
传感器与传感材料
·
农业人工智能
·
计算机视觉
·
智能包装
✓ 已验证
产品关联
DOI
高影响因子
MICROCHEMICAL JOURNAL
·
2026
·
IF 5.2
Xuqing Wang,Zheer Huang,Mengze Fu,Jiye Wang,Shurong Hou,Yingsheng He,Yazhou Qin,Xiabin Chen
SERS detection of five etomidate compounds in environmental water was achieved. • The minimum observable concentration of the five etomidate compounds in environmental water was 2 ng/mL. • CNN-AT model achieved 99.27% accuracy with the lowest standard deviation of 0.33%. • A visual analysis was conducted on the features extracted by the CNN-AT model. Environmental water bodies are directly related to human health. Monitoring emerging pollutants such as etomidate analogs in environmental water can provide important support for combating illegal drug abuse. In this study, an interpretable classification strategy was developed to distinguish etomidate analogs with highly similar structures and highly overlapping surface-enhanced Raman spectroscopy (SERS) spectra in spiked environmental water, achieving a minimum observable concentration of 2 ng/mL. Density functional theory (DFT) was further employed to assign substance-specific molecular vibrational fingerprints and to elucidate the relationship between substituents and spectral features. Finally, we developed a convolutional neural network model integrating a hybrid attention mechanism (CNN-AT) for classifying five structurally similar substances, achieving an accuracy of 99.27%. The results show that the developed model outperforms decision tree (DT), partial least squares discriminant analysis (PLS-DA), K-nearest neighbors (KNN), support vector machine (SVM), long short-term memory (LSTM), and Transformer models in accuracy. Moreover, analysis using gradient-weighted class activation mapping (Grad-CAM) visualization indicates that the model's classification focuses on characteristic peaks related to the molecular structure of the drugs, thereby enhancing the model's interpretability and transparency. Download: Download high-res image (100KB) Download: Download full-size image
✓ 已验证
产品关联
DOI
高影响因子
Current Research in Food Science
·
2026
·
IF 7.7
Wenyang Zhang,You Tian,Yanwu Chen,Min Wei
Given the perishable nature of seafood, accurate and rapid freshness monitoring is essential for ensuring food safety and public health. In this study, a ratiometric fluorescent tag was proposed for detecting ammonia to assess seafood freshness, using D-penicillamine-capped silver/copper nanoclusters (DPA-AgCuNCs) and fluorescein isothiocyanate (FITC) as dual-emission probes. The synthesized DPA-AgCuNCs with aggregation-induced emission (AIE) properties exhibited high sensitivity toward ammonia, with a limit of detection of 2.95 ppm (3σ/s). By integrating orange-emitting DPA-AgCuNCs with green-emissive FITC, the fabricated ratiometric fluorescent tag exhibited a distinct orange-to-green fluorescence transition with increasing ammonia concentration, enabling direct visual assessment of freshness. A fluorescence colour card was further established for rapid preliminary differentiation among fresh, less fresh, and spoiled samples. Convolutional neural network (CNN)-assisted image analysis was introduced as a complementary approach to improve the objectivity and consistency of freshness classification, achieving precision values of 95.24%, 100%, and 100% for fresh, less fresh, and spoiled shrimp, respectively. For on-site monitoring, the CNN was integrated into a smartphone application (FreshSense), constructing a simple platform for rapid monitoring of seafood freshness. This proof-of-concept system is rapid, on-site, and non-destructive, demonstrating its potential for practical screening in food quality and safety.
✓ 已验证
DOI
高影响因子
SEPARATION AND PURIFICATION TECHNOLOGY
·
2023
·
IF 8.6
Shuyuan Zhang,Haoran Li,Kai Wang,Tong Qiu
Deep learning has recently been leveraged in the microfluidic research for intelligent image processing. However, it usually requires massive human efforts to label sufficient images for obtaining a precise deep learning model. We herein propose an integrated microfluidic image processing method based on transfer deep learning for the rapid deployment of Mask R-CNN, which is capable of reutilizing models trained in previous microfluidic domains to accelerate the analysis of droplets and bubbles in the images of the target microfluidic domain. The transfer deep learning is validated in the microfluidic research with a constrictive microchannel, which is commonly used to break large droplets or bubbles to enhance emulsification. With only 40 labeled images and about 10 min training, the integrated image processing method achieves precise recognition results for both droplets and bubbles in the microfluidic experiments. Applying the trained Mask R-CNN to unlabeled images, the breakup of droplets is found to be highly dependent on the low flow rate, but the bubble breakup is much easier to happen in the same microfluidic equipment. Critical conditions of droplet breakup and size laws of droplet and bubble are precisely determined based on the recognition results of the trained Mask R-CNN.
研究领域:
微流控
·
人工智能
·
图像处理
·
深度学习
✓ 已验证
产品关联
DOI
高影响因子
Journal of Innovative Optical Health Sciences
·
2022
·
IF 2.396
Xiao Ma,Honglian Xiong,Jinhao Guo,Zhiming Liu,Yaru Han,Mingdi Liu,Yanxian Guo,Mingyi Wang,Huiqing Zhong,Zhouyi Guo
Because the breast cancer is an important factor that threatens women’s lives and health, early diagnosis is helpful for disease screening and a good prognosis. Exosomes are nanovesicles, secreted from cells and other body fluids, which can reflect the genetic and phenotypic status of parental cells. Compared with other methods for early diagnosis of cancer (such as circulating tumor cells (CTCs) and circulating tumor DNA), exosomes have a richer number and stronger biological stability, and have great potential in early diagnosis. Thus, it has been proposed as promising biomarkers for diagnosis of early-stage cancer. However, distinguishing different exosomes remain is a major biomedical challenge. In this paper, we used predictive Convolutional Neural model to detect and analyze exosomes of normal and cancer cells with surface-enhanced Raman scattering (SERS). As a result, it can be seen from the SERS spectra that the exosomes of MCF-7, MDA-MB-231 and MCF-10A cells have similar peaks (939, 1145 and 1380 cm − 1 ). Based on this dataset, the predictive model can achieve 95% accuracy. Compared with principal component analysis (PCA), the trained CNN can classify exosomes from different breast cancer cells with a superior performance. The results indicate that using the sensitivity of Raman detection and exosomes stable presence in the incubation period of cancer cells, SERS detection combined with CNN screening may be used for the early diagnosis of breast cancer in the future.
研究领域:
癌症生物学
·
生物医学工程
·
医学诊断
·
机器学习
✓ 已验证
产品关联
DOI
高影响因子
危险品化学品经营许可证（带存储）