检索结果-内蒙古大学图书馆

Near-Infrared Spectroscopy-Based Chilled Fresh Lamb Quality Detection Using Machine Learning Algorithms

JOURNAL OF FOOD SAFETY 2024年第5期44卷

作者： Li, Xinxing Wei, Changhui liang, buwen China Agr Univ Coll Informat & Elect Engn Beijing Peoples R China Nanchang Inst Technol Nanchang Peoples R China

Traditionally methods for assessing mutton quality rely on physical and chemical examination analyses that necessitate precise experimental environment conditions and specialized knowledge, often resulting in the compromise of the sample's structural integrity. To address these challenges, this study explores the application of near-infrared spectroscopy (NIR) as a non-destructive alternative for mutton quality evaluation, leveraging its operational simplicity, rapid analysis capabilities, and minimal requirement for technical expertise. Among various spectral data preprocessing techniques evaluated, multiple scattering correction (MSC) was found to significantly enhance model detection performance. Furthermore, principal component analysis (PCA) combined with the Mahalanobis Distance method was utilized for outlier identification. Finally, a mutton freshness detection model is constructed based on stacking ensemble learning, yielding an impressive accuracy rate of 0.976, outperforming other advanced approaches. In conclusion, our findings establish a robust theoretical framework for the rapid and non-destructive assessment of meat freshness, contributing to advancements in meat quality detection. Overview of the Technical ***

关键词： freshness lamb near-infrared spectroscopy stacking ensemble learning

来源：评论

学校读者我要写书评

暂无评论

An impedance-based beef freshness detection method using GcForest learning model

引用

JOURNAL OF FOOD MEASUREMENT AND CHARACTERIZATION 2025年第6期19卷 1-12页

作者： Li, Xinxing Li, Shu Tian, Jianjun liang, buwen China Agr Univ Coll Informat & Elect Engn Beijing 100083 Peoples R China Nanchang Inst Technol Nanchang 330044 Peoples R China Inner Mongolia Agr Univ Coll Food Sci & Engn Hohhot Peoples R China China Agr Univ Beijing 100083 Peoples R China

Effective quality assessment methods are critical for ensuring the safety of beef, a globally significant protein source. This study introduces a rapid, non-destructive approach leveraging the gcForest algorithm to evaluate beef freshness through bioimpedance spectroscopy. Fresh beef samples (hind leg, collected <= 48 h post-slaughter) were stored at 0 degrees C, 4 degrees C, 10 degrees C, and 25 degrees C to simulate real-world conditions. Total Volatile Basic Nitrogen (TVB-N) levels, a key freshness indicator, were correlated with impedance measurements acquired via two- and four-electrode configurations across 10 excitation frequencies (100 Hz-150 kHz). To optimize model robustness, the framework integrated OCSVM-based outlier detection, LASSO regression for feature selection, and PCA for dimensionality reduction. The gcForest algorithm, employing a deep forest architecture with multi-granularity scanning, demonstrated superior performance over conventional machine learning models (Decision Tree, Random Forest, AdaBoost, etc.). Notably, the four-electrode configuration achieved exceptional accuracy, with evaluation metrics (MAE: 0.8150, MSE: 0.9611, RMSE: 0.9803, R-2: 0.9208) outperforming the two-electrode setup (MAE: 0.8281, RMSE: 0.9902, R-2: 0.8953), attributable to enhanced signal fidelity in capturing microbial-driven impedance *** non-invasive method enables precise, real-time freshness assessment, providing actionable insights for food safety systems. Its operational simplicity and reliability position it as a transformative tool for meat quality control, with direct applications in supply chain monitoring and consumer health protection.

关键词： Freshness detection Four-electrode configuration GC forest Bioimpedance measurement TVB-N (Total volatile basic Nitrogen)

来源：评论

学校读者我要写书评

暂无评论

Incorporating Bioimpedance Technique with Ensemble Learning Algorithm for Mutton Tenderness Detection

引用

FOOD AND BIOPROCESS TECHNOLOGY 2023年第12期16卷 2761-2771页

作者： liang, buwen Wei, Changhui Li, Xinxing Zhang, Ziyi Huang, Xiaoyan China Agr Univ Coll Informat & Elect Engn Beijing 100083 Peoples R China Nanchang Inst Technol Nanchang 330044 Peoples R China

To elucidate the role of bioimpedance technique in meat quality detection, we measured the impedance phase and modulus of chilled mutton with different storage time and temperature using 2-electrode and 4-electrode, respectively, and then generated the high-resolution impedance map. Nevertheless, tenderness, an important standard for the meat quality, is difficult to detect by relying only on electrode materials and impedance measurement approaches due to its nonlinearity and fuzziness. To overcome this challenge, we proposed a mutton tenderness detection method that incorporates the bioimpedance technique with an ensemble learning algorithm to improve the performance. This approach utilizes the advantages of multiple classical machine learning algorithms, such as SVM, ANN, and random forest, from a data-driven perspective. Importantly, we also introduced the lasso method to find significant impedance features that are more effective in improving the accuracy of the algorithm. The results showed that the stacking ensemble learning-based model exhibits the highest performance with an accuracy of 0.960, 0.986, and an F1-score of 0.969, 0.978 for 2- and 4-electrode, respectively, which are much higher than that of single machine learning algorithm. In conclusion, the proposed method demonstrated that ensemble learning algorithm can significantly improve the accuracy and efficiency of mutton tenderness detection. Furthermore, it also indicated that improving the model algorithm is also an important direction to promote the meat quality detection.

关键词： Mutton tenderness Meat quality detection Bioimpedance Stacking ensemble learning

来源：评论

学校读者我要写书评

暂无评论

SARS-CoV-2 Spike Protein Post-Translational Modification Landscape and Its Impact on Protein Structure and Function via Computational Prediction

引用

Research 2023年第3期2023卷 757-767页

作者： buwen liang Yiying Zhu Wenhao Shi Can Ni Bowen Tan Shaojun Tang The Hong Kong University of Science and Technology(Guangzhou) GuangzhouChina Analysis Center Chemistry DepartmentTsinghua UniversityBeijingChina The Hong Kong University of Science and Technology Hong Kong SARChina

To elucidate the role of post-translational modifications(PTMs)in severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)spike protein’s structure and virulence,we generated a high-resolution map of 87 PTMs using liquid chromatography with tandem mass spectrometry data on the extracted spike protein from SARS-CoV-2 virions and then reconstituted its structure heterogeneity caused by ***,Alphafold2,a high-accuracy artificial intelligence tool to perform protein structure prediction,relies solely on primary amino acid sequence,whereas the impact of PTM,which often modulates critical protein structure and function,is much *** overcome this challenge,we proposed the mutagenesis approach—an in silico,site-directed amino acid substitution to mimic the influence of PTMs on protein structure due to altered physicochemical properties in the post-translationally modified amino acids—and then reconstituted the spike protein’s structure from the substituted sequences by *** the first time,the proposed method revealed predicted protein structures resulting from PTMs,a problem that Alphafold2 has yet to *** an example,we performed computational analyses of the interaction of the post-translationally modified spike protein with its host factors such as angiotensin-converting enzyme 2 to illuminate binding ***,this study suggested the structural analysis of post-translationally modified protein via mutagenesis and deep *** summarize,the reconstructed spike protein structures showed that specific PTMs can be used to modulate host factor binding,guide antibody design,and pave the way for new therapeutic *** code and Supplementary Materials are freely available at https://***/LTZHKUSTGZ/SARS-CoV-2-spike-protein-PTM.

关键词： translational substituted overcome

来源：评论

学校读者我要写书评

暂无评论

Fusion of hyperspectral and RGB images for exogenous matter residue detection in Atlantic salmon

引用

JOURNAL OF FOOD COMPOSITION AND ANALYSIS 2025年 143卷

作者： Li, Xinxing Wei, Changhui Zhang, Yingang Ma, Diankun Shi, Wenhao liang, buwen China Agr Univ Coll Informat & Elect Engn Beijing 100083 Peoples R China Nanchang Inst Technol Nanchang 330044 Peoples R China Open Univ China Beijing Peoples R China Tsinghua Univ Anal Ctr Chem Dept Beijing 100084 Peoples R China

Atlantic salmon is widely popular due to its delicious flesh and high nutritional value. However, improper production and processing may lead to the presence of foreign matter, which, if ingested by consumers, can pose serious risks. Traditional methods for detecting Atlantic salmon flesh foreign matter primarily rely on manual inspections, resulting in low efficiency. The introduction of hyperspectral detection technology and RGB image detection technology has significantly advanced research in food safety detection. However, hyperspectral detection technology is expensive, involves complex procedures, and is difficult to implement on a large scale;RGB image detection technology, on the other hand, is susceptible to interference from foreign matter with similar colors and shapes, leading to subpar detection performance. Modern detection studies have mainly focused on the identification of endogenous foreign matter, while research on exogenous foreign matter detection has been long neglected. To address these issues, this study proposed an innovative method based on the fusion of hyperspectral sensitive bands and RGB channels. We used the SeAFusion algorithm to fuse hyperspectral and RGB images, and constructed the Atlantic salmon flesh foreign matter detection dataset based on the RGB images and fused images. Building on this, three object detection algorithms-Faster R-CNN, YOLOv7, and YOLOv8-were introduced to develop a detection model for exogenous foreign matter in Atlantic salmon flesh. Ultimately, the model based on the YOLOv8 object detection algorithm demonstrated the best performance. On the fused image dataset, the overall detection accuracy reached 0.908, with an F1 score of 0.952 and an AP value of 0.952. These metrics surpass those of other advanced models by 0.5 %, 0.2 %, and 0.9 %, respectively. This study provides efficient technical support to ensure the quality and safety of Atlantic salmon, lays theoretical foundation for the development of low-co

关键词： Atlantic salmon Foreign matter detection Fusion image Deep learning

来源：评论

学校读者我要写书评

暂无评论

Forecasting greenhouse air and soil temperatures: A multi-step time series approach employing attention-based LSTM network

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2024年 217卷

作者： Li, Xinxing Zhang, Lu Wang, Xiangyu liang, buwen China Agr Univ Coll Informat & Elect Engn Beijing 100083 Peoples R China Nanchang Inst Technol Nanchang 330044 Peoples R China China Agr Univ Beijing 100083 Peoples R China

Greenhouses stand as key infrastructural components in contemporary agriculture, facilitating the perennial availability of vegetables. Harnessing accurate, real-time environmental data, particularly air and soil temperature, is pivotal to promoting the facility's efficiency in pest and disease alarming and vegetable production. Nevertheless, despite consistent long-term temperature trends, short-term fluctuations prove to be considerably nonlinear, time-lagged, and multivariate-coupled due to the unique microclimate of the greenhouse. Addressing this, we propose a novel short-term multi-step prediction model that assimilates a range of environmental data including air temperature, humidity, soil temperature, and soil moisture content at diverse greenhouse heights. This model utilizes an Attention-LSTM based time series approach to accurately predict multi-step short-term temperature variations within the greenhouse. By employing a modest amount of historical data (approximately 48 h), the model provides future temperature forecasts within a range of 30 to 480 min with high accuracy. When benchmarked against renowned models such as RNN, GRU, and LSTM networks, our proposed models display impressive performance. It achieved R2 values of 0.93, 0.94, 0.95, and 0.86 for 1, 4, 8, and 16-step predictions, respectively, in the domain of air temperature forecasting. The corresponding MSE values stood at 0.42, 0.32, 0.27, and 0.81. In parallel, for soil temperature forecasts, our model recorded R2 values of 0.96, 0.94, 0.92, and 0.89 for 1, 4, 8, and 16-step predictions, respectively, alongside MSE values of 0.36, 0.48, 0.73, and 0.99 for the equivalent steps. To conclude, these results reveal the exceptional predictive aptitude of our model for both air and soil temperature forecasts within greenhouse environments, validating its standing as an effective tool for the optimization of vegetable farming practices. Consequently, our model demonstrates its ability to yield preci

关键词： Facility agriculture Greenhouse Air temperature Soil temperature Time series Attentional mechanism

来源：评论

学校读者我要写书评

暂无评论

A XGBoost-Based Prediction Method for Meat Sheep Transport Stress Using Wearable Photoelectric Sensors and Infrared Thermometry

引用

SENSORS 2024年第23期24卷 7826页

作者： Ma, Ruiqin Chen, Runqing liang, buwen Li, Xinxing China Agr Univ Natl Res Facil Pheontyp & Genotyp Anal Model Anim Beijing 100083 Peoples R China China Agr Univ Coll Informat & Elect Engn Beijing 100083 Peoples R China

Transportation pressure poses a serious threat to the health of live sheep and the quality of their meat. So, the edible Hu sheep was chosen as the research object for meat sheep. We constructed a systematic biosignal detecting, processing, and modeling method. The biosignal sensing was performed with wearable sensors (photoelectric sensor and infrared temperature measurement) for physiological dynamic sensing and continuous monitoring of the transport environment of meat sheep. Core waveform extraction and modern spectral estimation methods are used to determine and strip out the target signal waveform from it for the purpose of accurate sensing and the acquisition of key transport parameters. Subsequently, we built a qualitative stress assessment method based on external manifestations with reference to the Karolinska drowsiness scale to establish stage classification rules for monitoring data in the transportation environment of meat sheep. Finally, machine learning algorithms such as Gaussian Naive Bayes (GaussianNB), Passive-Aggressive Aggregative Classifier (PAC), Nearest Centroid (NC), K-Nearest Neighbor Classification (KNN), Random Forest (RF), Support Vector Classification (SVC), Gradient Boosting Decision Tree (GBDT), and eXtreme Gradient Boosting (XGB) were established to predict the classification models of transportation stress in meat sheep. Their classification results were compared. The results show that SVC and GBDT algorithms are more effective and the overall model classification accuracy reached 86.44% and 91.53%. XGB has the best results. The accuracy of the assessment of the transport stress state of meat sheep after the optimization of three parameters was 100%, 90.91%, and 93.33%, and the classification accuracy of the overall model reached 94.92%. The final results achieved improve transport reliability, reduce transport risk, and solve the problems of inefficient meat sheep transport supervision and quality control.

关键词： meat sheep transport stress biosensing wearable IoT machine learning

来源：评论

学校读者我要写书评

暂无评论

Stacking ensemble learning for gas sensor-based detection of salmon freshness and shelf life

引用

JOURNAL OF FOOD PROCESS ENGINEERING 2024年第3期47卷 e14593-e14593页

作者： liang, buwen Li, Xinxing Yang, Mingsong Zhang, Ziyi Ren, Jie China Agr Univ Coll Informat & Elect Engn Beijing Peoples R China Nanchang Inst Technol Nanchang Peoples R China Forest Resource Monitoring & Protect Serv Ctr Yant Yantai Peoples R China China Agr Univ Beijing 100083 Peoples R China

Salmon, celebrated for its nutrition and flavor, suffers rapid degradation in freshness due to prolonged transportation and storage, offering a haven for microorganisms. Addressing the escalating need for safe, fresh fish consumption, we probed conventional chemical and physical indicators like total volatile basic nitrogen (TVB-N), pH, texture profile analysis (TPA), and chromaticity across varying temperature intervals, linking these with gas sensors to identify sensitive sensor arrays. Importantly, an ensemble learning strategy for gas sensors, synthesizing the benefits of Linear, SVR, MLP, KNN, Gaussian Process, and decision tree algorithms, was employed for prompt and precise detection of salmon freshness and shelf-life. Notably, the results demonstrated that gas sensors exhibited strong correlations, surpassing .8 for TVB-N and .5 for shelf life, underscoring their aptitude for detecting salmon spoilage gas. Additionally, ensemble learning outperformed singular machine learning algorithms, with stacking emerging preeminent, achieving R2 values of .851 and .871, and MSEs of .120 and 1.573, for TVB-N and shelf-life detection, respectively. In summation, this study introduces an avant-garde mechanism that amplifies the detection efficacy of gas sensors for salmon freshness, marrying them with stacking ensemble learning paradigms for cost-effective and efficient determinations. In conclusion, we devised a novel method to augment the detection efficacy of gas sensors for salmon freshness. By integrating these sensors with stacking ensemble learning algorithms, we achieved a data-driven, cost-effective, and efficient approach, fulfilling the requirements of salmon freshness *** applicationsMost existing gas sensors gas sensors predominantly employ singular machine learning methodologies, often limiting them to a sole freshness evaluation metric during assessments. This study introduces a pioneering approach using a stacking ensemble learning-based ga

关键词： freshness gas sensor salmon shelf life stacking ensemble learning TVBN

来源：评论

学校读者我要写书评

暂无评论

PEDE: Enhance Multi-modal Sarcasm Detection in Videos via Prompted Emotion Distributions

PEDE: Enhance Multi-modal Sarcasm Detection in Videos via Pr...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiaoqiang Zhang Ying Chen Guangyao Li buwen liang College of Information and Electrical Engineering China Agricultural University Beijing China Tsinghua University Beijing China University of Copenhagen Copenhagen Denmark

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Multi-modal sarcasm detection is crucial for understanding human communications. A key aspect of multi-modal sarcasm detection is the analysis of emotion incongruity. However, the advancement of emotion analysis in video is hindered by the scarcity of labeled datasets, which are limited in both scale and diversity due to high human annotation cost. In this paper, to deal with different kinds of emotion distributions of open-topic in video data, we propose a simple yet remarkably effective method named Prompted Emotion Distribution Enhancement (PEDE). This method leverages large-scale pre-trained models to generate emotion distributions, thereby enriching the input features for sarcasm detection models. Then, intra- and inter-modality emotion graphs are constructed and a graph attention network (GAT) is used to learn emotion incongruity in input. Extensive experiments demonstrate that our approach can significantly enhance the performance of existing multi-modal sarcasm detection approaches on a sarcasm video dataset.

关键词： Costs Annotations Speech enhancement Signal processing Feature extraction Data models Acoustics

来源：评论

学校读者我要写书评

暂无评论

A review: antimicrobial resistance data mining models and prediction methods study for pathogenic bacteria

引用

JOURNAL OF ANTIBIOTICS 2021年第12期74卷 838-849页

作者： Li, Xinxing Zhang, Ziyi liang, buwen Ye, Fei Gong, Weiwei China Agr Univ Coll Informat & Elect Engn Beijing Peoples R China China Acad Railway Sci Corp Ltd Transportat & Econ Res Inst Beijing Peoples R China

Antimicrobials have paved the way for medical and social development over the last century and are indispensable for treating infections in humans and animals. The dramatic spread and diversity of antibiotic-resistant pathogens have significantly reduced the efficacy of essentially all antibiotic classes and is a global problem affecting human and animal health. Antimicrobial resistance is influenced by complex factors such as resistance genes and dosing, which are highly nonlinear, time-lagged and multivariate coupled, and the amount of resistance data is large and redundant, making it difficult to predict and analyze. Based on machine learning methods and data mining techniques, this paper reviews (1) antimicrobial resistance data storage and analysis techniques, (2) antimicrobial resistance assessment methods and the associated risk assessment methods for antimicrobial resistance, and (3) antimicrobial resistance prediction methods. Finally, the current research results on antimicrobial resistance and the development trend are summarized to provide a systematic and comprehensive reference for the research on antimicrobial resistance.

关键词： Antimicrobial therapy Infection Life Sciences general Microbiology Medicinal Chemistry Organic Chemistry Bacteriology Bioorganic Chemistry

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：