检索结果-内蒙古大学图书馆

Advancing smart transportation: A review of computer vision and photogrammetry in learning-based dimensional road pavement defect detection

引用

COMPUTER SCIENCE REVIEW 2025年 56卷

作者： Tafida, Adamu Alaloul, Wesam Salah Zawawi, Noor Amila Bt Wan Musarat, Muhammad Ali Sani, Adamu Abubakar Univ Teknol PETRONAS Dept Civil & Environm Engn Bandar Seri Iskandar 32610 Perak Malaysia Univ Teknol PETRONAS Inst Autonomous Syst Offshore Engn Ctr Bandar Seri Iskandar 32610 Perak Malaysia Abubakar Tafawa Balewa Univ Dept Quant Surveying Bauchi Nigeria Abubakar Tafawa Balewa Univ Dept Bldg Bauchi Nigeria

Road infrastructure networks are crucial in facilitating smart mobility, as indicated by the emergence of innovative transportation concepts that offer improved efficiency and environmental sustainability. This study seeks to review the literature regarding road pavement condition assessment performance improvement tools which utilize various computer vision and photogrammetry tools aided by machine learning algorithms towards mitigating challenges encountered and promoting smart transportation trends. A comprehensive search of available literature was conducted, and relevant studies were analyzed to identify computer vision and photogrammetry tools used, learning-based algorithms deployed and contribution to the improvement of road infrastructure to aid smart transportation. The review considered emerging challenges of the techniques, identified research gaps and explored the potentials of the techniques as it relates to aiding wider acceptance of the implementation of autonomous vehicles and smart transportation The study found gaps in knowledge relating to the computer vision (CV) and photogrammetry tools standardization of evaluation parameters, the applicability of the models for real-time assessment and implications regarding the adoption of autonomous vehicles and smart transportation which were not sufficiently considered in the previous cited literature. Future research areas were highlighted and its implication regarding the promotion of smart transportation.

关键词： Smart transportation Road infrastructure Computer vision and photogrammetry machine learning algorithm Road defect detection

来源：评论

学校读者我要写书评

暂无评论

Numerical thermodynamic-economic study and machine learning-based optimization of an innovative biogas-driven integrated power plant combined with sustainable liquid CO2 and liquid H2 production-storage processes

引用

CASE STUDIES IN THERMAL ENGINEERING 2025年 69卷

作者： Yuan, Ruijia Shi, Fan Abed, Azher M. Shaban, Mohamed Samad, Sarminah Almadhor, Ahmad Abdullaeva, Barno Aoudia, Mouloud Alkhalaf, Salem Babiker, Samah G. Anhui Univ Finance & Econ Sch Management Sci & Engn Bengbu Peoples R China Al Mustaqbal Univ Coll Engn & Technol Air Conditioning & Refrigerat Tech Engn Dept Babylon 51001 Iraq Al Mustaqbal Univ Al Mustaqbal Ctr Energy Res Babylon 51001 Iraq Islamic Univ Madinah Fac Sci Dept Phys Madinah 42351 Saudi Arabia Princess Nourah Bint Abdulrahman Univ Coll Business Adm Dept Management Riyadh 11671 Saudi Arabia Jouf Univ Coll Comp & Informat Sci Dept Comp Engn & Networks Sakaka Saudi Arabia Tashkent State Pedag Univ Dept Math & Informat Technol Vice Rector Sci Affairs Tashkent Uzbekistan Northern Border Univ Dept Ind Engn Coll Engn POB 1321 Ar Ar 91431 Saudi Arabia Qassim Univ Coll Comp Dept Comp Engn Buraydah Saudi Arabia Red Sea Univ Fac Appl Sci Dept Elect Phys Port Sudan Sudan

Innovative heat recovery, CO2 capture, and energy storage methodologies are pivotal for developing sustainable and eco-friendly solutions for the energy sector. Hence, this study proposes implementing an oxyfuel combustion process for a biogas power plant, modified by an innovative heat recovery method and a CO2 capture-liquefaction technique. Furthermore, the design incorporates high-temperature water electrolysis to produce hydrogen, which is then introduced into a hydrogen liquefaction process utilizing a Claude cycle for adequate long-term storage. The research employs thermodynamic, exergoeconomic, and net present value assessments, accompanied by an extensive parametric study and optimization process. Hence, a machine learning algorithm is implemented using artificial neural networks combined with the NSGA-II method for multi-criteria optimization, focusing on exergy efficiency, net present value, and products' sum unit cost as objective functions. The implemented optimization reduces the optimization time to under 30 min, which is significantly more efficient than traditional heuristic techniques, which typically require several hours for similar systems. This optimization framework is highly applicable to both industrial and district energy systems. This approach enhances predictive analytics and streamlines resource management. In industrial environments, it effectively optimizes energy use and production processes by examining various operational factors, which leads to cost reductions and improved efficiency via predictive maintenance and cohesive energy strategies. The optimal outcomes reveal the mentioned objective functions' values at 47.22 %, 58.73 M$, and 33.53 $/GJ, respectively. Under these optimal conditions, liquid carbon dioxide and liquid hydrogen outputs are quantified at 4931 lit/h and 1848 lit/h, respectively. Finally, the proposed system can omit CO2 emissions by 1.36 kg/kWh under optimal conditions, which reflects a 5.60 % better performan

关键词： Environmental challenges Biogas Oxyfuel combustion process Carbon dioxide capture-liquefaction Liquid hydrogen storage machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

SERS-ATB: A comprehensive database server for antibiotic SERS spectral visualization and deep-learning identification

引用

ENVIRONMENTAL POLLUTION 2025年 373卷 126083页

作者： Yuan, Quan Tang, Jia-Wei Chen, Jie Liao, Yi-Wen Zhang, Wen-Wen Wen, Xin-Ru Liu, Xin Chen, Hui-Jin Wang, Liang Xuzhou Med Univ Sch Med Informat & Engn Xuzhou Jiangsu Peoples R China Shengli Oilfield Cent Hosp Dept Lab Med Dongying Shandong Peoples R China Southern Med Univ Guangdong Prov Peoples Hosp Guangdong Acad Med Sci Lab Med Guangzhou Guangdong Peoples R China Xuzhou Med Univ Sch Clin Med 1 Dept Clin Med Xuzhou Jiangsu Peoples R China Univ Queensland Sch Agr & Food Sci Brisbane Qld Australia Edith Cowan Univ Ctr Precis Hlth Sch Med & Hlth Sci Perth WA Australia Univ Western Australia Sch Biomed Sci Div Microbiol & Immunol Crawley WA Australia

The rapid and accurate identification of antibiotics in environmental samples is critical for addressing the growing concern of antibiotic pollution, particularly in water sources. Antibiotic contamination poses a significant risk to ecosystems and human health by contributing to the spread of antibiotic resistance. Surfaceenhanced Raman spectroscopy (SERS), known for its high sensitivity and specificity, is a powerful tool for antibiotic identification. However, its broader application is constrained by the lack of a large-scale antibiotic spectral database crucial for environmental and clinical use. To address this need, we systematically collected 12,800 SERS spectra for 200 environmentally relevant antibiotics and developed an open-access, web-based database at http://***/. We compared six machine learning algorithms with a convolutional neural network (CNN) model, which achieved the highest accuracy at 98.94%, making it the preferred database model. For external validation, CNN demonstrated an accuracy of 82.8%, underscoring its reliability and practicality for real-world applications. The SERS database and CNN prediction model represent a novel resource for environmental monitoring, offering significant advantages in terms of accessibility, speed, and scalability. This study establishes the large-scale, public SERS spectral databases for antibiotics, facilitating the integration of SERS into environmental programs, with the potential to improve antibiotic detection, pollution management, and resistance mitigation.

关键词： Antibiotic Surface-enhanced Raman spectroscopy Raman spectra machine learning algorithm Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Rapid response to pressure variations in water distribution networks through machine learning-enhanced data acquisition

引用

AQUA-WATER INFRASTRUCTURE ECOSYSTEMS AND SOCIETY 2024年第7期73卷 1358-1371页

作者： Kim, Hyunjun Jung, K. J. Lee, S. Jeong, E. H. Pusan Natl Univ Dept Mech Engn 2 Busandaehak Ro63 Beon Gil Busan South Korea Flowork Lab Res & Dev Dept 8 Seojeon Ro Busan South Korea

This study investigates rapid dynamic pressure variations in water distribution networks due to critical incidents such as pipe bursts and valve operations. We developed and implemented a machine learning (ML)-based methodology that surpasses traditional slow cycles of pressure data acquisition, facilitating the efficient capture of transient phenomena. Employing the Orion ML library, which features advanced algorithms including long short-term memory dynamic threshold, autoencoder with regression, and time-series anomaly detection using generative adversarial networks, we engineered a system that dynamically adjusts data acquisition frequencies to enhance the detection and analysis of anomalies indicative of system failures. The system's performance was extensively tested using a pilot-scale water distribution network across diverse operational conditions, yielding significant enhancements in detecting leaks, blockages, and other anomalies. The effectiveness of this approach was further confirmed in real-world settings, demonstrating its operational feasibility and potential for integration into existing water distribution infrastructures. By optimizing data acquisition based on learned data patterns and detected anomalies, our approach introduces a novel solution to the conventionally resource-intensive practice of high-frequency monitoring. This study underscores the critical role of advanced ML techniques in water network management and explores future possibilities for adaptive monitoring systems across various infrastructural applications. HIGHLIGHTS Developed a machine learning (ML)-based system to dynamically monitor pressure in water networks. Utilized advanced Orion ML library algorithms for real-time anomaly detection. Enhanced operational efficiency by optimizing data acquisition rates. Demonstrated effectiveness in pilot and real-world water distribution settings. Integrated Orion ML library with advanced algorithms to improve infrastructure resilience.

关键词： data acquisition machine learning algorithm network anomaly detection operational insight pressure wave detection water distribution network

来源：评论

学校读者我要写书评

暂无评论

Multi-response Optimization of 3D Printed Parts with Triangular Patterns Using Nonlinear machine learning Regressor Technique

引用

JOURNAL OF MATERIALS ENGINEERING AND PERFORMANCE 2024年 1-17页

作者： Tandon, Sourabh Singh, Sanjay Kumar Kacker, Ruchin Gautam, Satyam Shivam Tamang, Santosh Kumar Indian Inst Technol Bhubaneswar Bhubaneswar Orissa India Sagar Inst Sci & Technol Dept Mech Engn Bhopal Madhya Pradesh India NERIST Dept Mech Engn Itanagar Arunachal Prade India

In the ever-changing field of additive manufacturing, this work implemented machine learning algorithm (nonlinear regression approach) to find out the optimal tensile strength and modulus of elasticity of 3D-printed ABS, PLA, and PLA + CF components using MATLAB R2021a. The work navigates the complex interactions among material type, orientation, and infill density using a complex experimental design matrix. With an impressive accuracy rate of more than 90%, the nonlinear model proves to be a useful tool for predicting mechanical properties in the context of 3D printing. The study uses the desirability technique as part of a multi-response optimization strategy to achieve optimal performance. By using this procedure, the best process parameters are identified, and the result is a composite desirability score of 0.84. An orientation fixed at 0 degrees, a material type defined as PLA + CF, and an infill density set at 80% comprise the identified peak of efficiency. In addition, the ideal parameters for the responses of Elasticity Modulus and Tensile Strength are 80% infill density, 90 degrees orientation, and PLA material type. These results not only identify the best possible configurations, but also offer a detailed insight into the complex relationship between printing settings and the mechanical qualities that are produced. A Validation tests is carried out to demonstrate that the model is reliable and has a predicted accuracy of more than 90%. This strong validation demonstrates how well the model works in real-world scenarios and gives rise to confidence in its capacity to direct additive manufacturing procedures toward improved mechanical performance. This work essentially illuminates the intricacies of 3D printing parameters and provides a clear path for maximizing mechanical qualities, making it a lighthouse in the field of additive manufacturing. The research findings offer significant assistance for engineers and designers who aim to optimize their processe

关键词： additive manufacturing machine learning algorithm mechanical properties optimization

来源：评论

学校读者我要写书评

暂无评论

machine learning approach for the effectual production of a novel esterase and its application in bioremediation of dairy effluent

引用

PROCESS BIOCHEMISTRY 2024年 144卷 20-37页

作者： Sounderarajan, Sathieesh Karuppusamy, Kanakalakshmi Surya, Aafreen Periyar Vikram Puchalapalli, Dinesh Sankar Reddy Sethi, Gautam Ayothiraman, Seenivasan Natl Inst Technol Andhra Pradesh Dept Chem Engn Tadepalligudem 534101 Andhra Pradesh India Natl Inst Technol Andhra Pradesh Dept Biotechnol Biochem Engn Res Grp Tadepalligudem 534101 Andhra Pradesh India Indian Inst Technol Madras Dept Chem Engn Chennai 600036 Tamil Nadu India Bharathidasan Univ Dept Biotechnol Tiruchirappalli 620024 Tamil Nadu India Natl Univ Singapore NUS Ctr Canc Res Yong Loo Lin Sch Med Dept Pharmacol Singapore Singapore

The present work intends to maximize the production of an industrially important novel esterase from Trichoderma harzianum using both machine learning and statistical approaches and its application in the bioremediation of dairy effluent. Significant medium compounds, such as almond oil, casein, NaH 2 PO 4 , and trace elements, were screened from a pool of carbon, nitrogen, oil and surfactant sources along with other micronutrients using a first order statistical design. The optimum value of screened parameters was found using response surface methodology that resulted in the maximum esterase production of 2985.31 U/L. Artificial neural network trained with the experimental response of RSM experiments coupled with genetic algorithm optimization technique has resulted in the maximum esterase production of 3256.73 U/L, which is 150-folds higher as compared to the unoptimized condition and also found to be the higher than the outcome of statistical optimization. Dairy effluent was used for the production of esterase as well as for its bioremediation. At 50% load, the maximum reduction in chemical oxygen demand and the production of esterase were observed to be 46.84% and 34.12 U/ L, respectively. The COD reduction of diary effluent was modelled using Michaelis-Menten kinetics and the kinetic parameters, half saturation constant (K m ) and maximum reaction rate (r max ) value were evaluated as 286.88 mg/L and 26.04 mg/L/d, respectively.

关键词： Esterase Trichoderma harzianum Optimization machine learning algorithm Dairy effluent treatment

来源：评论

学校读者我要写书评

暂无评论

Optimizing Wire Electrical Discharge Machining Parameters for Enhanced Gear Machining Performance: A machine learning Approach on 20MnCr5 Steel

引用

JOURNAL OF MATERIALS ENGINEERING AND PERFORMANCE 2024年 1-13页

作者： Vijayakumar, N. Chandradass, J. SRM Inst Sci & Technol Fac Engn & Technol Ctr Automot Mat Sch Mech EngnDept Automobile Engn Kattankulathur Campus Chennai 603203 Tamil Nadu India

Gears are machine elements that require high precision and surface quality to attain elevated performance of machinery. Many traditional techniques are capable of manufacturing gears but still need to overcome many drawbacks that require post-processing treatments to overcome. Wire electric discharge machining is an inevitable machining process for making gears with superior properties and quality characteristics. The current study explores the optimization of WEDM process parameters by hybridizing Taguchi-Multi criteria decision making-Supervised machine learning techniques toward output responses material removal rate, profile error, and surface roughness for 20MnCr5 steel material Five different WEDM parameters such as arc on time, arc off time, servo voltage, wire tension and wire feed rate have been varied in three levels to develop the experimental design matrix through Taguchi's orthogonal array with 27 experimental trails. The output responses have been analyzed through a signal-to-noise ratio method to identify optimal parameter settings and further analyzed through the CRITIC-TOPSIS technique for ranking the alternatives. The closeness coefficient values are analyzed through ANOVA and found that arc on time (71.38%) and wire tension (16.51%) have significant contributions toward combined objectives. Both decision tree and kNN algorithms have achieved a better classification accuracy of more than 90% indicating their potential in predicting future outcomes at 75:25 split ratio. Arc on time is the most significant factor in all the output responses studied as per response table rankings, ANOVA results, and decision tree structure. This study demonstrated the efficiency of combining experimental data with MCDM and ML to optimize WEDM parameters for enhanced gear machining.

关键词： 20MnCr5 steel machine learning algorithm MRR profile error surface roughness WEDM

来源：评论

学校读者我要写书评

暂无评论

The Utility Impact of Differential Privacy on Credit Card Data in machine learning algorithms

引用

Procedia Computer Science 2023年 221卷 664-672页

作者： Xiaopeng LUO Siyuan WANG Haolong CHEN Zongwei LUO BNU-UIC Institute of AI and Future Networks Beijing Normal University Zhuhai China 519000

With the development of networks and financial technologies, credit card data is increasingly being used in various fields of data analysis such as user behavior, financial transactions, and market analysis. These fields often use multiple machine learning algorithms for data mining on credit card dataset. It is worth noting that credit card data contains more diverse and comprehensive information compared to traditional data, and the dataset may contain multiple data types. At the same time, credit card data may also expose users’ privacy information. Differential privacy algorithms can add random noise to the data set, protecting sensitive information while ensuring certain data utility. However, there has been little research on the use of differential privacy algorithms on credit card data in multiple machine learning algorithms, and there has been insufficient exploration of the utility impact of differential privacy on complex credit card data. These research gaps exist in both the financial technology and privacy protection industries. Therefore, this paper applies differential privacy to credit card data in multiple classic machine learning algorithms, discusses the utility impact of various differential privacy algorithms on credit card data, and compares the performance of credit card data sets protected by differential privacy in different algorithms.

关键词： credit card default differential privacy machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

machine learning algorithms for Chromophoric Dissolved Organic Matter (CDOM) Estimation Based on Landsat 8 Images

引用

REMOTE SENSING 2021年第18期13卷 3560-3560页

作者： Sun, Xiao Zhang, Yunlin Zhang, Yibo Shi, Kun Zhou, Yongqiang Li, Na Chinese Acad Sci State Key Lab Lake Sci & Environm Nanjing Inst Geog & Limnol Nanjing 210008 Peoples R China

Chromophoric dissolved organic matter (CDOM) is crucial in the biogeochemical cycle and carbon cycle of aquatic environments. However, in inland waters, remotely sensed estimates of CDOM remain challenging due to the low optical signal of CDOM and complex optical conditions. Therefore, developing efficient, practical and robust models to estimate CDOM absorption coefficient in inland waters is essential for successful water environment monitoring and management. We examined and improved different machine learning algorithms using extensive CDOM measurements and Landsat 8 images covering different trophic states to develop the robust CDOM estimation model. The algorithms were evaluated via 111 Landsat 8 images and 1708 field measurements covering CDOM light absorption coefficient a(254) from 2.64 to 34.04 m(-1). Overall, the four machine learning algorithms achieved more than 70% accuracy for CDOM absorption coefficient estimation. Based on model training, validation and the application on Landsat 8 OLI images, we found that the Gaussian process regression (GPR) had higher stability and estimation accuracy (R-2 = 0.74, mean relative error (MRE) = 22.2%) than the other models. The estimation accuracy and MRE were R-2 = 0.75 and MRE = 22.5% for backpropagation (BP) neural network, R-2 = 0.71 and MRE = 24.4% for random forest regression (RFR) and R-2 = 0.71 and MRE = 24.4% for support vector regression (SVR). In contrast, the best three empirical models had estimation accuracies of R-2 less than 0.56. The model accuracies applied to Landsat images of Lake Qiandaohu (oligo-mesotrophic state) were better than those of Lake Taihu (eutrophic state) because of the more complex optical conditions in eutrophic lakes. Therefore, machine learning algorithms have great potential for CDOM monitoring in inland waters based on large datasets. Our study demonstrates that machine learning algorithms are available to map CDOM spatial-temporal patterns in inland waters.

关键词： machine learning algorithm support vector regression (SVR) Gaussian process regression (GPR) chromophoric dissolved organic matter (CDOM) Landsat 8

来源：评论

学校读者我要写书评

暂无评论

machine learning Regression for Assessing Sensing Performance and Anticancer Potential of Oolong Tea-Derived Silver Nanoparticles

引用

JOURNAL OF THE ELECTROCHEMICAL SOCIETY 2025年第3期172卷 037503-037503页

作者： Sert, Esra Kalindemirtas, Ferdane Danisman Karakus, Emir Ersel Erol, Ayse Ozbas, Fatih Kucukdeniz, Tarik Karakus, Selcan Istanbul Univ Istanbul Fac Med Dept Hematol TR-34390 Istanbul Turkiye Erzincan Binali Yildirim Univ Fac Med Dept Physiol Erzincan Turkiye Private Nazmi Arikan Sci Sch TR-34906 Istanbul Turkiye Istanbul Univ Istanbul Fac Med Dept Med Biol Istanbul Turkiye Fatih Sultan Mehmet Vakif Univ Fac Arts Design & Architecture Dept Restorat & Conservat Cultural Assets TR-34015 Istanbul Turkiye Istanbul Univ Cerrahpasa Fac Engn Dept Ind Engn TR-34320 Istanbul Turkiye Istanbul Univ Cerrahpasa Fac Engn Dept Chem TR-34320 Istanbul Turkiye Hlth Biotechnol Joint Res & Applicat Ctr Excellenc TR-34220 Istanbul Turkiye

In this study, machine learning (ML) algorithms were employed to predict analyte concentrations using sensing results and evaluate the anticancer effects of nanostructures. Multifunctional oolong tea extract-mediated silver nanoparticles (OTE-Ag NPs) were synthesized via a photo/ultrasound method and utilized in various applications, including a smartphone-based H2O2 sensor and electrochemical sensors for urea and fructose. Key features were extracted from electrochemical results, and feature importance analysis was used to select the most predictive features. The artificial neural network (ANN) model provided accurate predictions, particularly strong for urea (R2 = 0.8575, RMSE = 0.4266, MAE = 0.3380). The study revealed the selective toxicity of OTE-Ag NPs to MCF-7 breast cancer cells through analyses of cytotoxicity, apoptosis, cell cycle phases, and CD44 surface marker expression using Annexin V/PI dye and flow cytometry. Experimental results demonstrated that OTE-Ag NPs suppressed MCF-7 cell proliferation while exhibiting lower cytotoxicity in normal HUVEC cells (46% cell death). OTE-Ag NPs arrested MCF-7 cells in the G2/M phase, induced apoptosis, and reduced CD44 expression, suggesting metastasis suppression. The CD44+/CD24- ratio decreased from 84.79% in control MCF-7 cells to 47.7% in OTE-Ag NP-treated cells. Overall, OTE-Ag NPs significantly inhibited MCF-7 cell proliferation through the apoptotic pathway by regulating the cell cycle in the G2/M phase.

关键词： machine learning algorithm artificial neural network apoptosis silver nanoparticles breast cancer electrochemical sensor

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：