SENSORS AND ACTUATORS B-CHEMICAL
·
2022
·
IF 9.221
Rui Huang,Yi Zhou,Jiaxiang Hu
Latent fingerprints (LFPs) are important trace evidences found at crime scenes that assist forensic experts in human identification, and a growing number of studies show that LFPs have some medical value. Herein, as one of the common nanoenzymes, Fe 3 O 4 nanoparticles (Fe 3 O 4 NPs) was used for LFPs imaging due to its excellent superparamagnetic properties and for recognition of glucose/H 2 O 2 on LFPs because of its horseradish peroxidase-like activity, which makes it possible to diagnose diabetes non-invasively through LFPs. Furthermore, the intelligent qualitative and semi-quantitative analysis of glucose/H 2 O 2 on LFPs was achieved by designing the classifier based on the multi-channel convolutional neural network (MC-CNN) technology. The qualitative accuracy rate is over 97% and the semi-quantitative accuracy rate reaches 90%. This work offers the promise to facilitate cross-disciplinary studies between artificial intelligence methods and fingerprint development technique.
研究领域:
法医学
·
纳米生物学
·
人工智能
✓ 已验证
产品关联
DOI
高影响因子
FOOD CHEMISTRY
·
2023
·
IF 8.8
Xiaotong Wang,Shen Jiang,Zhehan Liu,Xiaomeng Sun,Zhe Zhang,Xubin Quan,Tian Zhang,Weikang Kong,Xiaotong Yang,Yang Li
Pesticide residue poses a significant global public health concern, necessitating improved detection methods. Here, a novel platform was introduced based on surface-enhanced Raman spectroscopy (SERS) to detect ten distinct types of pesticides. Notably, the sensitivity of this approach is exemplified by detecting trace amounts of 50 pM (10 ppt) thiabendazole. The correlation between the characteristic peak intensity of coexisting pesticides and their concentrations displays an exceptional linear relationship (R 2 = 0.9999), underscoring its utility for quantitative mixed pesticide detection. Additionally, qualitative analysis of five mixed pesticides was conducted leveraging distinctive peak labeling. Harnessing machine learning techniques, a model for classifying and predicting pesticides on pericarps was developed. Remarkably, the convolutional neural network achieved classification accuracy of 100 % and prediction accuracy of 99.62 %. This innovative approach accurately identifies and quantifies diverse pesticides, thus offering a feasible scheme for in-situ detection of pesticide residues. Ultimately, this strategy contributes to ensuring food safety and public health.
研究领域:
食品科学
·
分析化学
·
人工智能
✓ 已验证
产品关联
DOI
PubMed
高影响因子
Journal of Materials Chemistry A
·
2023
·Vol. 11
·期 34
·18441-18453
·
IF 11.9
Junjun Huang,Wenqing Zhang,Xin Chen,Sanlong Wang,Zhenming Chen,Peng Li,Honglin Li,Chengmei Gui
Textile-based triboelectric nanogenerators (T-TENGs) have great potential in new-generation tactile sensors because their output signal is determined by the specific charge interaction between the target and triboelectric material. However, gesture recognition by existing T-TENG tactile sensors is very challenging because the electron affinity and polarity of the volunteer skin are similar. This study proposes a new structural sensor that integrates a Ni particle-encapsulated carbon tube (Ni@C tube) with polydimethylsiloxane (PDMS) by means of multiple strain mechanisms for improving recognition accuracy using a signal superposition technique. Interestingly, dynamic strain from multiple sources, i.e., PDMS layer strain (1.24–2.47 kPa), Ni@C tube crack (2.47–5.56 kPa), PDMS layer further strain (5.56–52.97 kPa), and Ni@C tube slip laterally (52.97–139.05 kPa), was established in the PDMS-coated Ni@C tube. In addition, the output signal of the as-fabricated T-TENG device was a combination of output signals from the PDMS/Ni@C tube and PDMS/contact object devices, which could fully reflect the stress field caused by the contact material pressing the surface and the surface characteristics, promoting the deep learning algorithm to be able to extract more hidden features of the identified materials. By integrating convolutional neural network (CNN) analysis based on the voltage signals of the T-TENG device, we explored a strategy that could enable the as-fabricated device to recognize 6 gestures with 99.3% recognition accuracy and 8 different materials with 99.8% recognition accuracy in the natural environment.
研究领域:
纳米技术
·
传感器技术
·
人工智能
·
材料科学
✓ 已验证
DOI
高影响因子
Artificial Intelligence in Agriculture
·
2025
·
IF 12.4
Zhizhong Sun,Jie Yang,Yang Yao,Dong Hu,Yibin Ying,Junxian Guo,Lijuan Xie
Visible/near-infrared (Vis/NIR) spectroscopy technology has been extensively utilized for the determination of soluble solids content (SSC) in fruits. Nonetheless, the spectral distortion resulting from temperature variations in the sample leads to a decrease in detection accuracy. To mitigate the influence of temperature fluctuations on the accuracy of SSC detection in fruits, using watermelon as an example, this study presents a knowledge-guided temperature correction method utilizing one-dimensional convolutional neural networks (1D-CNN). This method consists of two stages: the first stage involves utilizing 1D-CNN models and gradient-weighted class activation mapping (Grad-CAM) method to acquire gradient-weighted features correlating with temperature. The second stage involves mapping these features and integrating them with the original Vis/NIR spectrum, and then train and test the partial least squares (PLS) model. This knowledge-guided method can identify wavelength bands with high temperature correlation in the Vis/NIR spectra, offering valuable guidance for spectral data processing. The performance of the PLS model constructed using the 15 °C spectrum guided by this method is superior to that of the global model, and can reduce the root mean square error of the prediction set (RMSEP) to 0.324°Brix, which is 32.5 % lower than the RMSEP of the global model (0.480°Brix). The method proposed in this study has superior temperature correction effects than slope and bias correction, piecewise direct standardization, and external parameter orthogonalization correction methods. The results indicate that the knowledge-guided temperature correction method based on deep learning can significantly enhance the detection accuracy of SSC in watermelon, providing valuable reference for the development of PLS calibration methods.
研究领域:
食品科学
·
光谱学
·
人工智能
✓ 已验证
产品关联
DOI
高影响因子
Journal of Water Process Engineering
·
2022
·
IF 7.34
Yanting Qin,Hui Jia,Weixuan Liu,Na Lu,Huu Hao Ngo,Jie Wang
A low-cost in-situ micro laser transmission (IMLT) analysis system for particle size monitoring based on the principle of laser transmission extinction was developed to monitor the flocculation process . In this study, the IMLT system was used to obtain the voltage generated with the changes of flocculant dosage and floc sizes in different flocculation stages. A typical machine learning model, convolution neural network (CNN) method was built to manage the flocculant dosage, detection voltage and floc size to improve the accuracy of the correlation between the them. Results of IMLT revealed that the particle size of flocs was inversely proportional to the voltage, and a larger final voltage R value indicated better effects of flocculation and sedimentation. The correlation between the particle size obtained by CNN training and measured particle size was 42.4 % and 30.5 % higher than that without training at low and high concentrations, respectively. IMLT is effective in reflecting the floc sedimentation, stability and dynamic influence of the coagulant aid on flocculation system.
研究领域:
环境科学
·
水处理工程
·
机器学习应用
✓ 已验证
产品关联
DOI
高影响因子
Journal of Materials Chemistry C
·
2025
·Vol. 13
·期 18
·9382-9391
·
IF 5.1
Zaidong Chen,Yuefei Xiang,Xinghui Qin,Lei Zhong,Hong Liao,Shiwen Liu,Jiaqi Wang,Kezhi Zheng,Dejian Hou,Lei Zhou,Mingmei Wu
The challenges of low blue light absorption, reduced luminous efficiency, and low thermal stability are critical issues confronting near-infrared II (NIR-II) phosphors, which significantly hinder their applications in food testing, medical imaging, and various other fields. Herein, an energy transfer strategy was adopted to enhance blue light absorption by introducing Cr3+ into Lu2CaMg2Si3O12:Ni2+, thereby enhancing their luminescence properties, including quantum efficiency and thermal stability. Given the superior energy transfer efficiency of Cr3+ → Ni2+, the quantum efficiency of Lu2CaMg2Si3O12:Cr3+,Ni2+ was increased from 23.0% to 32.6%, and the thermal stability improved by 18%, as compared to Lu2CaMg2Si3O12:Ni2+. Furthermore, the Dexter's model was employed to systematically analyze the energy transfer mechanism of transition metal ions. In addition, due to the difference in the temperature response of Cr3+ and Ni2+, the thermometry performance of this phosphor was studied. Importantly, a pioneering method for food components detection based on the convolutional neural network model was proposed, demonstrating a 100% detection success rate. This research not only propels the development of novel blue-light-excitable NIR-II phosphors but also contributes to the advancement of intelligent lighting technologies.
研究领域:
材料科学
·
光学
·
人工智能
·
医学影像
✓ 已验证
产品关联
DOI
高影响因子
ADVANCED MATERIALS
·
2022
·Vol. 34
·期 29
·2203073
·
IF 32.086
Xuelian Wei,Baocheng Wang,Zhiyi Wu,Zhong Lin Wang
Robotic perception can have simple and effective sensing functions that are unreachable for humans using only the isolated tactile perception method, with the assistance of a triboelectric nanogenerator (TENG). However, the reliability of triboelectric sensors remains a major challenge due to the inherent environmental limitations. Here, an intelligent tactile sensing system that combines a TENG and deep-learning technology is proposed. Using a triboelectric triple tactile sensor array, typical characteristics of each testing material can be maintained stably even under different contact conditions (touch conditions and external environmental conditions) by extracting features from three independent electrical signals as well as the normalized output signals. Furthermore, a convolutional neural network model is integrated, and a high accuracy of 96.62% is achieved in a material identification task. The tactile sensing system is exhibited to an open environment for material identification and the real-time demonstration. Compared to the complex process that humans must integrate multiple sensing (touching and viewing) to accomplish tactile perception, the proposed sensing system shows a huge advantage in cognitive learning for the visually impaired, biomimetic prosthetics, and virtual spaces construction.
研究领域:
机器人学
·
传感器技术
·
人工智能
✓ 已验证
产品关联
DOI
PubMed
高影响因子
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
·
2022
·
IF 4.831
Yuanjie Teng,Zhenni Wang,Shaohua Zuo,Xin Li,Yinxin Chen
Universal and fast antibiotic residues detection technology is imperative for the control of food safety in aquatic products. However, accurate surface-enhanced Raman scattering (SERS) quantitative detection of complicated samples is still a challenge. A recognition method powered by deep learning and took advantage of the unique fingerprint information merits of SERS was proposed. Herein, the spectra were collected by Ag nanofilm SERS substrate prepared by self-assembly of Ag nanoparticles on water/oil interface. A SERS-based database of commonly used antibiotics in aquatic products was set up, which is suitable for employed as input data for learning and training. The results show that the five types of antibiotics are successfully distinguished through principal component analysis (PCA) and each antibiotic in every type was successfully distinguished. Furthermore, one-dimensional convolutional neural networks (1-D CNN) was used to distinguish the antibiotics, and the results show that all the test samples were correctly predicted by 1-D CNN model. The results of this research suggest the great potential of the combination of SERS spectra with deep learning as a method for rapid and highly accurate identification of antibiotic residues in aquatic products.
研究领域:
食品科学
·
分析化学
·
人工智能
✓ 已验证
产品关联
DOI
PubMed
高影响因子
ANALYTICAL CHEMISTRY
·
2023
·
IF 7.4
Xiaoqing Tan,Yongtao Tang,Tingting Yang,Guoliang Dai,Changqing Ye,Jianxin Meng,Fengyu Li
Photochromic sensors have the advantages of diverse isomers for multi-analysis, providing more sensing information and possessing more recognition units and more sensitivity to external stimulations, but they present enormous complexity with various stimulations as well. Deep learning (DL) algorithms contribute a huge advantage at analyzing nonlinear and multidimensional data, but they suffer from nontransparent inner networks, “black-boxes”. In this work, we employed the explainable DL approach to process and explicate photochromic sensing. Spirooxazine metallic complexes were adopted to prepare a multi-state analysis array for β-Lactams identification and quantitation. A dataset of 2520 unduplicated fluorescence intensity images was collected for convolutional neural network (CNN) operation. The method clearly discriminated six β-Lactams with 97.98% prediction accuracy and allowed rapid quantification with a concentration range from 1 to 100 mg/L. The photochromic sensing mechanism was verified via molecular simulation and class activation mapping, which explicated how the CNN model assesses the importance of photochromic sensor states and makes a discrimination decision. The explainable DL-assisted analysis method establishes an end-to-end strategy to ascertain and verify the complicated sensing mechanism for device optimization and even new scientific discovery.
研究领域:
分析化学
·
人工智能
·
药物分析
✓ 已验证
产品关联
DOI
PubMed
高影响因子
Journal of Energy Storage
·
2024
·
IF 8.9
Xiaoyong Gu,Peng Ding,Guojie Chao,Ying Cui
Lithium-ion batteries crucially rely on an effective battery thermal management system (BTMS) to sustain their temperatures within an optimal range, thereby maximizing operational efficiency. Incorporating bio-based composite phase change material (CPCM) into BTMS enhances efficiency and sustainability. This study commences by blending lauric acid and myristic acid in a 7: 3 mass ratio to synthesize a bio-based CPCM, following which the thermophysical properties of this CPCM are tested. Subsequently, the CPCM is integrated into a SiC foam and coupled with air to develop a novel BTMS. Then the effects of air velocity and initial temperature on the temperature of the battery pack are analyzed. Finally, the RIME-Convolutional Neural Network (CNN)- Self-Attention (SA)- Gated Recurrent Unit (GRU) model is established to predict the temperature of the battery in this BTMS. The results indicate that the latent heat of the CPCM is 97.98 J/g, melting at 35 °C upon heating. The incorporation of SiC foam-CPCM effectively reduces battery temperatures. When the air velocity is set at 3 m/s, the battery temperature remains below 40 °C during a discharge rate of 2C. Notably, the CPCM melts at higher initial temperatures, effectively mitigating the temperature rise in the battery pack. The RIME-CNN-SA-GRU model exhibits remarkable accuracy, with a maximum prediction error of 0.56 °C and a RMSE of 0.23, precisely capturing the trend of a sharp temperature rise at the end of discharge. This study presents an efficient solution for lithium-ion battery thermal management and temperature prediction.
研究领域:
材料科学
·
能源工程
·
人工智能
✓ 已验证
产品关联
DOI
高影响因子
Nanomaterials
·
2022
·Vol. 12
·期 12
·2114
·
IF 5.719
Bo Wang,Xiaoling Qin,Kun Meng,Liguo Zhu,Zeren Li
Terahertz (THz) spectroscopy is the de facto method to study the vibration modes and rotational energy levels of molecules and is a widely used molecular sensor for non-destructive inspection. Here, based on the THz spectra of 20 amino acids, a method that extracts high-dimensional features from a hybrid spectrum combined with absorption rate and refractive index is proposed. A convolutional neural network (CNN) calibrated by efficient channel attention (ECA) is designed to learn from the high-dimensional features and make classifications. The proposed method achieves an accuracy of99.9%and99.2%on two testing datasets, which are12.5%and23%higher than the method solely classifying the absorption spectrum. The proposed method also realizes a processing speed of 3782.46 frames per second (fps), which is the highest among all the methods in comparison. Due to the compact size, high accuracy, and high speed, the proposed method is viable for future applications in THz chemical sensors.
研究领域:
生物化学
·
人工智能
·
分子传感
✓ 已验证
DOI
高影响因子
Materials Horizons
·
2025
·
IF 10.7
Shufen Wang,Mengyu Li,Hailing Xiang,Wenlong Chen,Ruping Xie,Zhixiong Lin,Konghong Hu,Ning Zhang,Chengmei Gui
Tactile sensors based on triboelectric nanogenerators (TENGs) showed great potential for self-driven sensing in material identification. The existing TENG devices used strongly electrophilic materials as friction layers. For test materials with electrophilicity, their output signals are weak and difficult to efficiently recognize. Here, a TENG-based sensor with boron nitride nanosheets/waterborne epoxy (BNNSs/WEP) composites as the friction layer was proposed for improving the accuracy of identifying negative charged materials. During the process of contact friction with negative charged objects, the as-fabricated TENG device displayed excellent output performance, with a maximum output voltage of 2.7 V and a charge density of 88.32 nC m−2. Combining deep machine learning and the friction electric effect, we developed a material recognition system for TENG sensors with integrated fatigue testing, data processing, and display modules. Following the training of the convolutional neural network (CNN) model with friction electrical signals generated by TENGs, the model demonstrated high accuracy in recognizing eight different materials, with a confusion matrix accuracy of 100%. Then, a sensor was developed for real-time device monitoring, with recognition accuracy of 100%, 100%, 55% and 49% for four kinds of materials. This work will further facilitate the development of a material perception system in the machine intelligence field.
研究领域:
材料科学
·
机器学习
·
传感器技术
✓ 已验证
产品关联
DOI
PubMed
高影响因子
危险品化学品经营许可证（带存储）