检索结果-内蒙古大学图书馆

Improvement of blueberry freshness prediction based on machine learning and multi-source sensing in the cold chain logistics

引用

FOOD CONTROL 2023年 145卷

作者： Huang, Wentao Wang, Xuepei Zhang, Junchang Xia, Jie Zhang, Xiaoshuan China Agr Univ Coll Engn Beijing Lab Food Qual & Safety Beijing 100083 Peoples R China Shanghai Jiao Tong Univ Sch Informat & Elect Engn Shanghai 200240 Peoples R China China Agr Univ Sch Informat & Elect Engn Beijing 100083 Peoples R China China Agr Univ Beijing 100083 Peoples R China

Traditional fruit freshness prediction and modeling heavily rely on various physicochemical indicators (such as water loss rate, pH, and VC content), which is facing predicaments of time-consuming, laborious, destructive, and low prediction accuracy. To this end, this paper proposes a new method for fruit freshness prediction based on multi-sensing technology and machine learning algorithm, thereby improving the automation, intelligentialize, and high accuracy of fruit freshness prediction. The critical control points of blueberry cold chain logistics were analyzed firstly based on the HACCP method, identifying the key gas parameters (O2, CO2, and C2H4) and interaction mechanisms of gas and blueberry freshness. Then the blueberry cold chain microenvironment monitoring platform (BCCMMP) was developed for critical gas content monitoring at different temperatures (0 degrees C, 5 degrees C, and 22 degrees C). It was demonstrated that gas information can replace quality information to characterize blueberry freshness, and further emerging machine learning (ML) algorithms (BP, RBF, SVM, and ELM) were constructed for blueberry freshness prediction using critical gas information, and the results showed prediction accuracies of 90.87% (BP), 92.24% (RBF), 94.01% (SVM), and 91.31% (ELM). By contrast, the 85.10% prediction accuracy was achieved by the traditional Arrhenius equation method based on temperature and quality parameters. Through the automatic non-destructive acquisition of sensing data and emerging machine learning algorithms, this paper provides a new approach to improving the freshness prediction accuracy and food quality management level during fruit cold chain logistics.

关键词： Wireless sensor network (WSN) Blueberry Freshness prediction machine learning algorithm HACCP methods

来源：评论

学校读者我要写书评

暂无评论

Balancing phosphorus fertilization for sustainable maize yield and soil test phosphorus management: A long-term study using machine learning

引用

FIELD CROPS RESEARCH 2023年 304卷

作者： Gupta, Naveen Punjab Agr Univ Dept Soil Sci Ludhiana 141004 Punjab India

Context Excessive phosphorus (P) applications to ensure enhanced crop growth and increased profitability are commonly used, leading to declined P use efficiency and high P accumulation in most cultivated soils across north-western India. However, the effects of consistently applying excessive P fertilizers on soil test P (STP) levels, P availability, and maize production outcomes are poorly *** The study aims to find the long-term impacts of different fertilizer P application rates on maize yield, agronomic P efficiency, optimal P rates for yield maximization, and predictive models for sustainable crop production and environmental protection across soils with different STP *** The current study collected and analysed maize plant and soil data spanning from 2011 to 2021 from an ongoing long-term field experiment conducted on three different STP status soils i.e., medium P (MPS), high P (HPS), and very high P (VHPS) soils. The experiment involves five different fertilizer P application rates No-P, 13, 26, 39, and 52 kg P ha(-1).Results The results indicated a significant increase in maize grain yield and P bioavailability with the application of 13 kg ha(-1) of fertilizer P in VHPS (>50.0 kg P ha(-1)) and 26 kg ha(-1) in both HPS (22.5-0.0 kg P ha(-1)) and MPS ((1)2.5-22.5 kg P ha(-1)). Improved agronomic efficiency reducing P rate to half of the recommended 26 kg P ha(-1) was estimated in VHPS. The economically optimal P rate (EOPR) model consistently sustains crop yield with lower P rates. Among the different machine learning algorithms, multiple linear regression (MLR) was found more reliable in predictive accuracy. The decrease in predicted grain yield and increase in predicted soil P accumulation at P rates of 26 kg P ha(-1) and above in varying P status soils underscores the need for judicious P fertilization practices to avoid negative impacts on *** The P application required to obtain an average maize yield of 6000 k

关键词： Long-term fertilization Soil residual P Agronomic efficiency P uptake machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Using unmanned aerial vehicles (UAVs) and machine learning techniques for the assessment of Posidonia debris and marine (plastic) litter on coastal ecosystems

引用

REGIONAL STUDIES IN MARINE SCIENCE 2023年 67卷

作者： Zaaboub, Noureddine Guebsi, Ridha Chaouachi, Riadh Salah Brik, Bochra Rotini, Alice Chiesa, Stefania Rende, Sante Francesco Makhloufi, Mohamed Hamza, Asma Galgani, Francois El Bour, Monia Univ Carthage Natl Inst Marine Sci & Technol INSTM Marine Environm Lab 8 LR16INSTM04 Salammbo 2025 Tunisia Inst Natl Rech Sci Ctr Eau Terre Environm Quebec Equipe Rech Teledetect Environm & NORd TENOR Quebec City PQ Canada Italian Inst Environm Protect & Res ISPRA Via Vitaliano Brancati 48 I-00144 Rome Italy Ctr Oceanol Pacifique Vairao BP 49 F-98179 Tahiti French Polynesi France

Due to the dynamics of the littoral zone and continuous inputs from tidal oscillations, riverine sources, anthropogenic activity, and inputs from extreme events, the use of unmanned aerial vehicles (UAVs) for assessing marine litter and Posidonia deposits on beaches has become a necessity. In recent years, Posidonia oceanica beach wracks (banquette) along Mediterranean coasts have increased and are often associated with marine litter items, mostly plastic. In our study, we attempted to list marine litter and categorize the items from pictures The results show an abundance of plastic debris at the Kerkennah site, where the average value of plastic deposits exceeds 100 items per 170 m of beach length. In the second step, we used UAVs for 3D mapping of Posidonia deposits and identification of marine litter classes. The orthomosaic was used for rapid Posidonia volume quantification on beaches. machine learning was employed to assess MML (Marine-Macro Litter) abundance based on the orthophotos assembly. In the following step, we proceeded with ortho-mosaic creation and delimitation of the study area for the identification and analysis of macroplastics and other items using processed data. Our findings and image processing demonstrate that the K-nearest neighbor (KNN) approach yields excellent results compared to in situ quantification and assessment along the Kerkennah transect for four tests of macro plastic identification and quantification. The error of using UAVs was calculated with an average value of 6.3%, with bottle shape identification being the dominant result.(c) 2023 Elsevier B.V. All rights reserved.

关键词： Posidonia oceanica Marine litter Plastic Unmanned aerial vehicles machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Layer-Wise Adaptive Weighting for Faster Convergence in Federated learning 25

Layer-Wise Adaptive Weighting for Faster Convergence in Fede...

引用

25th IEEE International Conference on Information Reuse and Integration for Data Science (IEEE IRI)

作者： Lanjewar, Vedant S. Tran, Hai-Anh Tran, Truong X. Penn State Univ Sch Sci Engn & Technol Penn State Harrisburg Middletown PA 17057 USA Hanoi Univ Sci & Technol HOST Sch Informat & Commun Technol Hanoi Vietnam

ISBN: (纸本)9798350351194;9798350351187

Federated learning (FL), a decentralized approach utilizing multiple devices for training machine learning algorithms, presents an innovative solution to the challenges associated with handling sensitive personal data in neural network training. This research explores the application of FL for training neural network models, emphasizing its benefits in safeguarding privacy, optimizing efficiency, and addressing communication costs. While FL offers advantages such as enhanced data efficiency, promotion of heterogeneity, and scalability, challenges arise from the presence of non-independent and non-identically distributed data in the real world. This research introduces the FedLayerWise algorithm, a novel approach that dynamically assigns weights to each layer of clients' models based on their contributions to the global model. The algorithm leverages the relationship between gradients of the client model and the global model to adaptively modify weights post-training, expediting convergence towards optimal loss. Experimental results on the MNIST dataset with non-identical distributions demonstrate the algorithm's effectiveness. FedLayerWise outperforms existing algorithms (FedAdp and FedAvg) under highly skewed non-IID data distribution, achieving faster convergence. The proposed modifications showcase improvements and converge faster to non-IID data distributions, reducing computation rounds by about 40% compared to FedAdp and about 50% compared to FedAvg in such scenarios.

关键词： Federated learning Neural Networks Fast Convergence Rate machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

INTRAGRO: A machine learning approach to predict future growth of trees under climate change

引用

ECOLOGY AND EVOLUTION 2023年第10期13卷 e10626页

作者： Aryal, Sugam Griessinger, Jussi Dyola, Nita Gaire, Narayan Prasad Bhattarai, Tribikram Braeuning, Achim Friedrich Alexander Univ Erlangen Nurnberg Inst Geog Wetterkreuz 15 D-91058 Erlangen Bayern Germany Chinese Acad Sci Inst Tibetan Plateau Res State Key Lab Tibetan Plateau Earth Syst Resources Beijing Peoples R China Univ Quebec Chicoutimi Dept Sci Fondamentales Lab Ecosyst Terr Boreaux Chicoutimi PQ Canada Tribhuvan Univ Dept Environm Sci Patan Multiple Campus Lalitpur Nepal Tribhuvan Univ Cent Dept Biotechnol Kathmandu Nepal

The escalating impact of climate change on global terrestrial ecosystems demands a robust prediction of the trees' growth patterns and physiological adaptation for sustainable forestry and successful conservation efforts. Understanding these dynamics at an intra-annual resolution can offer deeper insights into tree responses under various future climate scenarios. However, the existing approaches to infer cambial or leaf phenological change are mainly focused on certain climatic zones (such as higher latitudes) or species with foliage discolouration during the fall season. In this study, we demonstrated a novel approach (INTRAGRO) to combine intra-annual circumference records generated by dendrometers coupled to the output of climate models to predict future tree growth at intra-annual resolution using a series of supervised and unsupervised machine learning algorithms. INTRAGRO performed well using our dataset, that is dendrometer data of P. roxburghii Sarg. from the subtropical mid-elevation belt of Nepal, with robust test statistics. Our growth prediction shows enhanced tree growth at our study site for the middle and end of the 21st century. This result is remarkable since the predicted growing season by INTRAGRO is expected to shorten due to changes in seasonal precipitation. INTRAGRO's key advantage is the opportunity to analyse changes in trees' intra-annual growth dynamics on a global scale, regardless of the investigated tree species, regional climate and geographical conditions. Such information is important to assess tree species' growth performance and physiological adaptation to growing season change under different climate scenarios.

关键词： dendrometer growing-season change intra-annual growth machine learning algorithm Pinus roxburghii sub-tropical Nepal

来源：评论

学校读者我要写书评

暂无评论

machine learning Strategies for Analyzing Road Traffic Accident 15th

Machine Learning Strategies for Analyzing Road Traffic Accid...

引用

15th International Conference on Intelligent Human-Computer Interaction (IHCI)

作者： Gupta, Sumit Kumar, Awadhesh BHU Inst Sci Dept Comp Sci Varanasi Uttar Pradesh India BHU Dept Comp Sci MMV Varanasi Uttar Pradesh India

ISBN: (纸本)9783031538261;9783031538278

Road safety and accidents have been an important concern for the entire world and everyone is putting effort into resolving the long-standing problem of road safety and accidents. In every country on earth, there is traffic and reckless driving. This has a negative impact on a lot of pedestrians. They become victims, although having done nothing wrong. The number of traffic accidents is rising quickly due to the enormous increase in road cars. Accidents like these result in harm, impairment, and occasionally even fatalities. Numerous things like weather changes, sharp curves, and human error all contribute to the high number of traffic accidents. In this research paper various machine learning techniques such as, K Nearest Neighbors, Random Forest, Logistic Regression, Decision Tree, and XGBoost etc., are used to investigate why road traffic accidents occur in various nations throughout theworld. For evaluating and analyzing these algorithm several metrics, including precision, recall, accuracy and F1-Score are used to improve the performance of the dataset and predicts accuracy by approximately more than 85%.

关键词： machine learning algorithm Supervised learning Feature Analysis Road Accident metric parameter

来源：评论

学校读者我要写书评

暂无评论

Translator attribution of Hongloumeng: using entropy-based features and machining learning algorithm

引用

DIGITAL SCHOLARSHIP IN THE HUMANITIES 2025年第1期40卷 138-150页

作者： Hu, Ruitao Wang, Gui Shao, Bin Zhejiang Univ Sch Int Studies 866 Yuhangtang Rd Hangzhou 310058 Zhejiang Peoples R China

This study utilized machine learning algorithms and entropy-based features to identify translators of two English translations of Hongloumeng, a great classical Chinese novel written in the mid-18th century. The translations under examination were completed, respectively, by David Hawkes and the Yangs (Yang Hsien-yi and Gladys Yang). Two feature sets were extracted as input for the identification of translator styles: wordform features (wordform unigrams, bigrams, and trigrams) and part-of-speech (POS) features (POS unigrams, bigrams, and trigrams). Additionally, four machine learning classifiers were tested: linear support vector machines (SVMs), linear discriminant analysis (LDA), random forest (RF), and multilayer perceptron (MLP). Analysis of feature importance and SHAP value identified the most influential features within each classifier. Results showed that LDA achieved the best performance, with 81 per cent accuracy in distinguishing between translations, showing promise for translator identification. In contrast, MLP struggled to reliably differentiate between translations, achieving only 50 per cent accuracy. Furthermore, POS features had the greatest influence in SVM and LDA, while wordform features dominated in RF. SHAP analysis revealed that Hawkes' translation tended to exhibit higher POS unigram and lower POS trigram entropy compared to the Yangs'. This increased contribution of POS unigrams and trigrams suggests a link to explicitation differences in translation. In summary, the combination of machine learning and entropy-based stylometric features shows potential for automatic translator identification and analysis.

关键词： Hongloumeng translator attribution entropy machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Unobtrusive machine learning based leg position detection during seated office work

Unobtrusive machine learning based leg position detection du...

引用

IEEE International Symposium on Medical Measurements and Applications (MeMeA)

作者： Ong, Linda Cao, Ming Verkerke, G. J. (Bart) Lamoth, C. J. C. (Claudine) Wilhelm, Elisabeth Univ Groningen Engn & Technol Inst Groningen Netherlands Univ Groningen Univ Med Ctr Groningen Dept Rehabil Med Groningen Netherlands Univ Groningen Univ Med Ctr Groningen Dept Human Movement Sci Groningen Netherlands

ISBN: (纸本)9798350308006;9798350307993

Musculoskeletal disorders (MSD) affect more than 1.63 billion people worldwide. Office workers are at high risk of developing MSD due to prolonged sitting during office work. Technical aids that provide users with insights into their sitting behaviour are useful for the prevention of MSD. Despite the fact that leg position is known to influence spine curvature, most position detection devices focus on upper body posture. In comparison, we recorded contact force with the chair using pressure sensors with the additional information from videos that showed the sitting position in 30 participants. Each participant was recorded during 5 working days resulting in a median recording time of 22 hours and 53 minutes. The active number of sensors, mean value and area under the curve of sensors in specific areas, feature extraction with convolution filters, and center of pressure were extracted from the force sensor values. An XGboost classification algorithm was trained on these features to discriminate between four different leg positions and the absence of a user. This algorithm obtained an overall accuracy of 73% on the test set consisting of 6 participants. The f1-scores for the classes 'away', 'no cross', 'knee cross', and 'ankle cross' were 0.96, 0.54, 0.76, and 0.44 respectively. The class legs on the chair, which rarely occurred in the monitored population, were mistaken for 'no cross' and could not be identified correctly in the test set. A second XGboost classifier was able to differentiate between symmetric and asymmetric sitting leg positions and away with a weighted accuracy of 85%. Overall pressure mats are a promising technology for observing common leg postures in office environments.

关键词： Decision support system machine learning algorithm Monitoring Musculoskeletal system Occupational Health Predictive model Pressure sensors

来源：评论

学校读者我要写书评

暂无评论

Harnessing Multi-satellite Remote Sensing Data and machine learning for Flood Risk Assessment in Nam Ngum River Basin, Lao PDR

Harnessing Multi-satellite Remote Sensing Data and Machine L...

引用

SPIE Future Sensing Technologies Conference

作者： Mangkhaseum, Sackdavong Duwal, Sunil Bhattarai, Yogesh Hanazawa, Akitoshi Kyushu Inst Technol Dept Elect & Space Syst Engn Kitakyushu Fukuoka Japan Khwopa Coll Engn Dept Civil Engn Bhaktapur Nepal

ISBN: (数字)9781510674905

ISBN: (纸本)9781510674905;9781510674899

The study focuses on flood susceptibility in the Nam Ngum River Basin, Lao PDR, an area prone to annual flooding due to monsoons and rainstorms. Flooding in this region significantly threatens human life, causes economic losses, and damages communities and agriculture. The study employs advanced remote sensing and machine learning techniques, including random forest (RF), support vector machine (SVM), and artificial neural networks (ANN), to address these issues and create detailed flood susceptibility maps. The machine learning models used historical flood data, Sentinel-1 SAR imagery from 2018 to 2020, and open-source flood data for training and validation. Eleven flood factors were considered. With 776 samples, 70% were trained, and 30% tested the model. Flood susceptibility map accuracy is assessed using statistical techniques such as multicollinearity, Kappa index, and area under the curve of receiver operating characteristics (AUROC). The generated flood susceptibility map is used to analyze the possible effect on the different land use/land cover classes and populations. RF outperforms SVM and ANN, achieving higher accuracy based on Receiver Operating Characteristics. The resulting flood susceptibility map reveals that 25-44% of the basin area is highly susceptible, predominantly in low-elevation and low-slope regions. Likewise, 85 to 90% of the people are highly vulnerable to flooding within 260 to 280 km2 of built-up area. The study proposes a new approach to using machine learning and readily available remote sensing data for flood susceptibility mapping. The findings of this study provide essential insights for policymakers, aiding in disaster risk reduction and facilitating sustainable development planning in Lao PDR.

关键词： Flood susceptibility modeling machine learning algorithm remote sensing risk assessment Nam Ngum River Basin Laos

来源：评论

学校读者我要写书评

暂无评论

Identification of key genes associated with oxidative stress in ischemic stroke via bioinformatics integrated analysis

引用

BMC NEUROSCIENCE 2025年第1期26卷 1-12页

作者： Li, Gaiyan Cheng, Yu Ding, Shanshan Zheng, Qianyun Kuang, Lanqiong Zhang, Ying Zhou, Ying Shanghai Xuhui Cent Hosp Dept Rehabil Shanghai Peoples R China Shanghai Xuhui Cent Hosp Dept Image Shanghai Peoples R China Shanghai Xuhui Cent Hosp Dept Gen Practice Shanghai Peoples R China

BackgroundIschemic stroke (IS) is a common cerebrovascular disease. Although the formation of atherosclerosis, which is closely related to oxidative stress (OS), is associated with stroke-related deaths. However, the role of OS in IS is ***-related key genes were obtianed by overlapping the differentially expressed genes (DEGs) between IS and normal control (NC) specimens, IS-related genes, and OS-related genes. Then, we investigated the mechanism of action of key genes. Subsequently, protein-protein interaction (PPI) network and machine learning algorithms were utilized to excavate feature genes. In addition, the network between feature genes and microRNAs (miRNAs) was established to investigate the regulatory mechanism of feature genes. Finally, quantitative PCR (qPCR) was utilized to validate the expression of feature genes with blood *** total of 42 key genes related to OS were acquired. Enrichment analysis indicated that the key genes were associated with oxidative stress, reactive oxygen species, lipid and atherosclerosis, and cell migration-related pathways. Then, 6 feature genes (HSPA8, NCF2, FOS, KLF4, THBS1, and HSPA1A) related to OS were identified for IS. Besides, 6 feature genes and 255 miRNAs were utilized to establish a feature genes-miRNA network which contained 261 nodes and 277 edges. At last, qPCR results revealed that there was a trend for higher expression of FOS, KLF4, and HSPA1A in IS specimens than in NC specimens. Additionally, HSPA8 expression was significantly decreased in the IS specimens, which was consistent with the findings of the GEO database *** conclusion, 6 feature genes (HSPA8, NCF2, FOS, KLF4, THBS1, and HSPA1A) related to OS were mined by bioinformatics analysis, which might provide a new insights into the evaluation and treatment of *** trial number: Not *** conclusion, 6 feature genes (HSPA8, NCF2, FOS, KLF4, THBS1, and HSPA1A) related to OS were mined

关键词： Ischemic stroke Oxidative stress machine learning algorithm WGCNA

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：