检索结果-内蒙古大学图书馆

Waste Material Classification Based on a Wavelength-Sensitive Ge-on-Si Photodetector

SENSORS 2024年第21期24卷 6970页

作者： Manakkakudy Kumaran, Anju De Iacovo, Andrea Ballabio, Andrea Frigerio, Jacopo Isella, Giovanni Colace, Lorenzo Roma Tre Univ Dept Ind Elect & Mech Engn Via Vito Volterra 62 I-00146 Rome Italy Eye4NIR Srl Via Bartolomeo Colleoni 14 I-23801 Calolziocorte Italy Politecn Milan Dipartimento Fis LNESS Via Anzani 42 I-22100 Como Italy

Waste material classification is critical for efficient recycling and waste management. This study proposes a novel, low-cost material classification system based on a single, voltage-tunable Ge-on-Si photodetector operating across the visible and short-wave infrared (SWIR) spectral regions. Thanks to its tunability, the sensor is able to extract spectral information, and the system effectively distinguishes between seven different materials, including plastics, aluminum, glass, and paper. The system operates with a broadband illuminator, and material identification is obtained through the processing of the photocurrent signal at different bias voltages with classification algorithms. Here, we demonstrate the basic system functionality and near real-time classification of different waste materials.

关键词： dual-band photodetector material classification machine learning algorithm optical sensor

来源：评论

学校读者我要写书评

暂无评论

Optimal gas sensor combination selection method for low cost machine olfaction applicated in food discrimination

引用

SENSORS AND ACTUATORS A-PHYSICAL 2024年 365卷

作者： Zhang, Ruoyu Chen, Dongliang Xing, Chong Wu, Qiuju Xu, Lei Univ Sci & Technol China Sch Microelect Hefei Peoples R China

In this paper an electronic nose system is proposed, together with odor-related gas information data processing and recognizing methods and an optimal gas sensor combination selecting procedure. The constructed electronic nose system consists of three parts, including a gas sensor chamber, data collecting circuits loaded with gas sensors and odor-related information data processing AI-driving programs. Utilizing the constructed electronic nose system, we accomplish the classifying missions of most 7 fruits and 8 vegetables to classifying accuracy of 96.7% using SVM classification algorithm and 10 sensor units. All probable gas sensor combinations are checked by the standard of their classifying performance to find the gas sensor combination match best when working together. The outcome turned to find that a specified gas sensor combination composed of 4 sensor units work best in the fruits and vegetables classification. This outcome suggests that these 4 sensor units are most suitable utilizing in related fruits and vegetables classification mission.

关键词： Odor recognition machine olfaction MOX gas sensor array machine learning algorithm Food discrimination

来源：评论

学校读者我要写书评

暂无评论

Cognitive workload classification of law enforcement officers using physiological responses

引用

APPLIED ERGONOMICS 2024年 119卷 104305页

作者： Wozniak, David Zahabi, Maryam Texas A&M Univ Wm Michael Barnes Dept Ind & Syst Engn 64 College Stn TX 77843 USA

Motor vehicle crashes (MVCs) are a leading cause of death for law enforcement officers (LEOs) in the U.S. LEOs and more specifically novice LEOs (nLEOs) are susceptible to high cognitive workload while driving which can lead to fatal MVCs. The objective of this study was to develop a machine learning algorithm (MLA) that can estimate cognitive workload of LEOs while performing secondary tasks in a patrol vehicle. A ride -along study was conducted with 24 nLEOs. Participants performed their normal patrol operations while their physiological responses such as heartrate, eye movement, and galvanic skin response were recorded using unobtrusive devices. Findings suggested that the random forest algorithm could predict cognitive workload with relatively high accuracy ( >70%) given that it was entirely reliant on physiological signals. The developed MLA can be used to develop adaptive in -vehicle technology based on real-time estimation of cognitive workload, which can reduce the risk of MVCs in police operations.

关键词： machine learning algorithm Law enforcement officers Adaptive technology

来源：评论

学校读者我要写书评

暂无评论

Bending fatigue properties and prediction of asphalt mixtures with ultra-large aggregates

引用

CONSTRUCTION AND BUILDING MATERIALS 2024年 414卷

作者： Tian, Tian Jiang, Yingjun Li, Sheng Nie, Chenliang Yi, Yong Zhang, Yu Deng, Changqing Changan Univ Key Lab Special Area Highway Engn Minist Educ South 2nd Ring RdMiddle Sect Xian 710064 Shaanxi Peoples R China Shaoyang Univ Coll Urban & Rural Construct Shaoyang 422000 Peoples R China

The laboratory fatigue test of asphalt mixture is generally carried out at a specific temperature, but previous studies have shown that the temperature range of flexible base is large, and the temperature has a significant effect on the performance of asphalt mixture. Therefore, the bending strength test was carried out to study the bending properties of ultra-large particle-size asphalt mixture (LSAM-50) at temperatures ranging from - 15 degrees C to 75 degrees C, and a prediction model of bending parameters considering temperature was established. Then, the effects of temperature (-15 degrees C to 35 degrees C) and stress level (0.3 to 0.9) on the fatigue life of LSAM-50 were studied by fourpoint bending fatigue test, and the experimental results were treated with Weibull distribution. Finally, four machine learning methods, including multiple linear regression method, sparrow search algorithm optimization back propagation (BP) neural networks, genetic algorithm optimization BP and enhanced whale optimization algorithm optimization BP, were used to achieve regression prediction of LSAM-50 equivalent fatigue life under 5% failure probability. The results show that the failure bending tensile strain, bending tensile strength, failure bending tensile modulus and temperature of LSAM-50 conform to the Boltzmann function. The strain and temperature are "S" type, while the strength, modulus and temperature are "inverted S". The average error of the prediction model is about 4.7%. The fatigue life decreases with the increase of temperature (or stress level). The input variables of the prediction model include temperature, stress level, stress, ratio of bending tensile strength to modulus, and the determination coefficient R2 is greater than 0.9. The results of this study can provide reference for the design of asphalt mixture.

关键词： Flexible base Ultra-large particle size asphalt mixture (LSAM-50) Bending fatigue property machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Using microwave-assisted extraction with advanced artificial intelligence models for predicting tannins in black pepper ( Piper nigrum L.)

引用

JOURNAL OF APPLIED RESEARCH ON MEDICINAL AND AROMATIC PLANTS 2025年 44卷

作者： Khajeh, Mostafa Ghaffari-Moghaddam, Mansour Piri, Jamshid Barkhordar, Afsaneh Senol, Halil Saloglu, Didem Univ Zabol Fac Sci Dept Chem Zabol Iran Univ Zabol Fac Water & Soil Dept Water Engn Zabol Iran Bezmialem Vakif Univ Fac Pharm Dept Pharmaceut Chem Istanbul Turkiye Istanbul Tech Univ Disaster Management Inst Dept Disaster & Emergency Management Istanbul Turkiye

Black pepper ( Piper nigrum L.) is a widely used spice that provides great potential for research in the field of natural products. In this work, the recovery of tannins from black pepper was conducted using microwave- assisted extraction (MAE). The study involves four independent variables: power (from 100 to 300 W), extraction time (from 10 to 40 minutes), temperature (from 35 to 50 degrees C), and the ratio of food to solvent (from 0.25 to 0.5 g/10 mL). The response variable was the extraction yield, which is the total tannin content. A total of 30 different experimental runs were completed in the MAE system. An evaluation and comparison of two non-verbal modeling approaches and artificial intelligence-based models was conducted. In order to predict design performance and results, the three SVR-RSM, M5Tree, and RM5Tree models were compared to a proposed nonlinear regression model. Evaluations were conducted using health criteria such as RMSE and NSE. With an RMSE of 0.035 and an NSE of 0.91, the SVR-RSM algorithm showed the highest level of accuracy. A RMSE of 0.048 and an NSE of 0.83 is obtained from the RM5tree model, while a RMSE of 0.055 and an NSE of 0.78 is obtained from the M5Tree model. Also, an NSE of 0.65 and a RMSE of 0.068 were obtained for the proposed nonlinear model. The SVR-RSM algorithm had maximum accuracy, but tree models for systems requiring a quick response are the right options. Using the proposed non-error model, complex relationships between variables could also be modeled.

关键词： Black pepper Microwave assisted extraction Performance prediction Nonlinear modeling machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

BaseNet: A transformer-based toolkit for nanopore sequencing signal decoding

引用

COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL 2024年 23卷 3430-3444页

作者： Li, Qingwen Sun, Chen Wang, Daqian Lou, Jizhong Chinese Acad Sci Inst Biophys Ctr Excellence Biomacromol Key Lab Epigenet Regulat & Intervent Beijing 100101 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Beijing Polyseq Biotech Co Ltd Beijing 100089 Peoples R China

Nanopore sequencing provides a rapid, convenient and high-throughput solution for nucleic acid sequencing. Accurate basecalling in nanopore sequencing is crucial for downstream analysis. Traditional approaches such as Hidden Markov Models (HMM), Recurrent Neural Networks (RNN), and Convolutional Neural Networks (CNN) have improved basecalling accuracy but there is a continuous need for higher accuracy and reliability. In this study, we introduce BaseNet (https://***/liqingwen98/BaseNet), an open-source toolkit that utilizes transformer models for advanced signal decoding in nanopore sequencing. BaseNet incorporates both autoregressive and non-autoregressive transformer-based decoding mechanisms, offering state-of-the-art algorithms freely accessible for future improvement. Our research indicates that cross-attention weights effectively map the relationship between current signals and base sequences, joint loss training through adding a pair of forward and reverse decoder facilitate model converge, and large-scale pre-trained models achieve superior decoding accuracy. This study helps to advance the field of nanopore sequencing signal decoding, contributes to technological advancements, and provides novel concepts and tools for researchers and practitioners.

关键词： Nanopore sequencing Basecall Transformer machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Beyond Butler-Volmer equation for CO2 electro-reduction on Cu-based gas diffusion electrodes

引用

CHEMICAL ENGINEERING JOURNAL 2025年 513卷

作者： Adesina, Peace Ager, Joel W. Lapkin, Alexei A. Univ Cambridge Dept Chem Engn & Biotechnol Philippa Fawcett DrWest Cambridge Site Cambridge CB3 0AS England CREATE Tower Cambridge Ctr Adv Res & Educ Singapore CARES 1 Create Way Singapore 138602 Singapore CREATE Tower Berkeley Educ Alliance Res Singapore BEARS 1 Create Way Singapore 138602 Singapore Lawrence Berkeley Natl Lab Chem Sci & Mat Sci Div Berkeley CA 94720 USA Univ Calif Berkeley Dept Mat Sci & Engn Berkeley CA 94720 USA

We present a methodology for modelling gas diffusion electrodes with Cu-based catalysts. The applicability of the Butler Volmer equation (B-V E) based on Tafel analysis is limited to single electron transfer reactions which are not typical of CO2 reduction reactions on Cu catalysts. We developed a method that involves linking the nanoscale effects encapsulated in a detailed calibrated microkinetic model (MKM) on Cu(100) electrodes to a mass transport model (MTM) on a low surface area, flooded agglomerate electrode. The MKM carries richer kinetic information of most reaction pathways described in contemporary literature for Cu(100). Polynomial equations are used to bridge kinetic and transport models without the need for excessive complexity. Our results show that using regression modelling, the microkinetic information at the microscopic level of the catalyst can be successfully linked with the macroscopic electrode models. We observe how mass transport parameters such as CO2 concentration, pH, and applied voltage, interacts with microkinetic information of the catalyst, influencing the reaction pathways and current densities of key products methane, ethylene, ethanol, and hydrogen. Although the model explores the medium to high voltage regimes, the methodology can address the oversimplification of CO2 reduction (CO2RR) kinetics and hydrogen evolution reaction (HER) for observed multiple kinetic regimes if comprehensive microkinetic models are integrated. It also serves as a foundational work for further experimental endeavours for the development of comprehensive microkinetic models. The holistic approach carried out in this work allows for the optimization of both reaction rates and mass transport, paving the way for rational optimisation of electrode designs and their scaling towards commercialization.

关键词： CO 2 electroreduction Copper gas diffusion electrodes Mass transport Butler Volmer equation Microkinetic model Data-driven surrogate modelling machine learning algorithm Multiscale modelling

来源：评论

学校读者我要写书评

暂无评论

Prediction of early neurological deterioration in acute minor ischemic stroke by machine learning algorithms

引用

CLINICAL NEUROLOGY AND NEUROSURGERY 2020年 195卷 105892-105892页

作者： Sung, Sang Min Kang, Yoon Jung Cho, Han Jin Kim, Nae Ri Lee, Suk Min Choi, Byung Kwan Cho, Giphil Pusan Natl Univ Hosp Sch Med Stroke Ctr Busan South Korea Pusan Natl Univ Hosp Sch Med Dept Neurol Busan South Korea Pusan Natl Univ Hosp Sch Med Dept Neurosurg Busan South Korea Pusan Natl Univ Hosp Sch Med Biomed Res Inst Busan South Korea Pusan Natl Univ Finance Fishery Mfg Ind Math Ctr Big Data Busan South Korea

Objectives: A significant proportion of patients with acute minor stroke have unfavorable functional outcome due to early neurological deterioration (END). The purpose of this study was to evaluate the applicability of machine learning algorithms to predict END in patients with acute minor stroke. Patients and methods: We collected clinical and neuroimaging information from patients with acute minor stroke with NIHSS score of <= 3. Early neurological deterioration was defined as any worsening of NIHSS score within 3 days after admission. Unfavorable functional outcome was defined as a modified Rankin Scale score of >= 2. We also compared clinical and neuroimaging information between patients with and without END. Four machine learning algorithms, i.e., Boosted trees, Bootstrap decision forest, Deep neural network, and Logistic Regression, were selected and trained by our dataset to predict early neurological deterioration Results: A total of 739 patients were included in this study. 78 patients (10.6%) experienced END. Among 78 patients with END, 61 (78.2%) had unfavorable functional outcome at 90 days after stroke onset. On multivariate analysis, the initial NIHSS score (P = 0.003), hemorrhagic transformation (P = 0.010), and stenosis (P = 0.014) or occlusion (P = 0.004) of a relevant artery were independently associated with END. Of the four machine learning algorithms, Boosted trees, Deep neural network, and Logistic Regression can be used to predict END in patients with acute minor stroke (Boosted trees: accuracy = 0.966, F1 score = 0.8 and area under the curve = 0.934, Deep neural network :0.966, 0.8, and 0. 904, and Logistic Regression : 0.966, 0.8, and 0.885). Conclusions: This study suggests that machine learning algorithms that integrate clinical and neuroimaging information can be used to predict END in patients with acute minor stroke. Further studies based on larger, multicenter datasets are needed to predict END accurately for designing treatment strate

关键词： Early neurological deterioration Acute ischemic minor stroke machine learning algorithm Functional outcome

来源：评论

学校读者我要写书评

暂无评论

Grey wolf optimizer integrated within boosting algorithm: Application in mechanical properties prediction of ultra high-performance concrete including carbon nanotubes

引用

APPLIED MATERIALS TODAY 2025年 42卷

作者： Ciftcioglu, A. Ozyuksel Kazemi, F. Shafighfard, T. Manisa Celal Bayar Univ Fac Engn Dept Civil Engn Manisa Turkiye Gdansk Univ Technol Fac Civil & Environm Engn Ul Narutowicza 11-12 PL-80233 Gdansk Poland Univ Naples Federico II Sch Polytech & Basic Sci Dept Struct Engn & Architecture Naples Italy POLISH ACAD SCI Inst Fluid Flow Machinery Gen Jozefa Fiszera 14 PL-80231 GDANSK Poland

Nowadays, the construction industry has increasingly recognized the superior performance characteristics of ultra high-performance concrete (UHPC). Known for its exceptional durability and high tensile strength, UHPC material is revolutionizing structure standards subjected to extreme environmental conditions and heavy loads. This paper explores the enhancement of UHPC with nano- and micromaterials, employing advanced machinelearning (ML) techniques to optimize the prediction of mechanical properties. Moreover, by introducing the novel extreme gradient boosting (XGBoost) improved by grey wolf optimizer (GWO) algorithm, this research represents the first integration of ML with GWO in UHPC research, significantly enhancing the accuracy of predictions for key properties such as compressive, tensile, and flexural strengths. The study investigates the impact of nanotechnology on UHPC, specifically how carbon nanotubes (CNTs) and microscale reinforcements contribute to advances in strength, durability, and resilience. These enhancements are pivotal in addressing limitations of traditional concrete, especially in high-demand construction environments. The proposed GWOXGB model has demonstrated a remarkable ability to achieve R2 values of 98.4% and 94.8% for UHPC with nanomaterial and micromaterial, respectively, indicating very high level of accuracy in predicting mechanical properties. This model also had one of the lowest error values, demonstrating its precision and ability to minimize prediction errors. This approach significantly facilitates the testing and development of UHPC by automating the accurate determination of its mechanical properties, thereby reducing the reliance on costly and time-consuming experimental methods. Highlighting the transformative potential of combining ML with engineering science, this study offers promising avenues for innovations in construction practices.

关键词： Ultra high-performance concrete Nanomaterial and micromaterial additive Grey wolf optimizer machine learning algorithm Mechanical property of carbon nanotube

来源：评论

学校读者我要写书评

暂无评论

Student Behavior Modeling for an E-learning System Offering Personalized learning Experiences

引用

Computer Systems Science & Engineering 2022年第3期40卷 1127-1144页

作者： K.Abhirami M.K.Kavitha Devi Department of Computer Science and Engineering Kings College of EngineeringPudukkottai613303India Department of Computer Science and Engineering Thiagarajar College of EngineeringMadurai625015India

With the advent of computing and communication technologies,it has become possible for a learner to expand his or her knowledge irrespective of the place and ***-based learning promotes active and independent *** scale e-learning platforms revolutionized the concept of studying and it also paved the way for innovative and effective teaching-learning *** digital learning improves the quality of teaching and also promotes educational ***,the challenges in e-learning platforms include dissimilarities in learner’s ability and needs,lack of student motivation towards learning activities and provision for adaptive learning *** quality of learning can be enhanced by analyzing the online learner’s behavioral characteristics and their application of intelligent instructional *** is not possible to identify the difficulties faced during the process through evaluation after the completion of e-learning *** is thus essential for an e-learning system to include component offering adaptive control of learning and maintain user’s interest *** this research work,a framework is proposed to analyze the behavior of online learners and motivate the students towards the learning process accordingly so as to increase the rate of learner’s objective *** to the demands of e-learner,an intelligent model is presented in this study for e-learning system that apply supervised machine learning *** adaptive e-learning system suits every category of learner,improves the learner’s performance and paves way for offering personalized learning experiences.

关键词： Learner behavior modeling e-learning intelligent learning system machine learning algorithm

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：