检索结果-内蒙古大学图书馆

IEEE Journal of Selected Areas in Sensors 2025年 2卷 84-107页

作者： Hassija, Vikas Chamola, Vinay De, Rajdipta Das, Soham Chakrabarti, Arjab Sangwan, Kuldip Singh Pandey, Amit Deemed to be University School of Computer Engineering Bhubaneswar751024 India BITS-Pilani Department of Electrical and Electronics Engineering Pilani Campus Pilani333031 India BITS Pilani Department of Mechanical Engineering Pilani Campus Pilani333031 India Bennett University Computer Science Engineering and Technology Department Greater Noida201310 India

Digital Twins, sophisticated digital replicas of physical entities, have been gaining significant attention, especially after NASA's endorsement, and are poised to revolutionize numerous fields, such as medicine and construction. These advanced models offer dynamic, real-time simulations, leveraging enabling technologies, such as artificial intelligence, machine learning, IoT, cloud computing, and Big Data analytics to enhance their functionality and applicability. In the medical field, Digital Twins facilitate personalized treatment plans and predictive maintenance of medical equipment by simulating human organs with precision. In construction, they enable efficient building design and urban planning, optimizing resource use, and reducing costs through predictive maintenance. Startups are innovatively employing Digital Twins in various sectors, from smart cities - where they optimize traffic flow, energy consumption, and waste management - to industrial machinery, ensuring predictive maintenance and minimizing downtime. This survey delves into the diverse use cases, market potential, and challenges of Digital Twins, such as data security and interoperability, while emphasizing their transformative impact on industries. The future prospects are promising, with continuous advancements in AI, ML, IoT, and cloud computing driving further expansion and application of Digital Twin technologies. © 2024 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Predicting Used Car Prices Employing Data Mining Techniques 3rd

Predicting Used Car Prices Employing Data Mining Techniques

引用

3rd International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2023

作者： Sai, P. H. V. Sesha Talpa Bharathi, V. V. Pratibha Lahari, M. L. R. Chaitanya Madalageri, Veeresh P. Marol, Vinodkumar S. Arun, C.K. Tiwari, Kishan Bhaumik, Amiya Department of Mechanical Engineering Malla Reddy College of Engineering and Technology Hyderabad India Department of Mechanical Engineering Mahaveer Institute of Science and Technology Hyderabad India School of Mechanical Engineering Lincoln University College Petaling Jaya Malaysia Department of Computer Science and Engineering Malla Reddy University Hyderabad India Lincoln University College Petaling Jaya Malaysia

ISBN: (纸本)9789819783540

A significant number of cars are purchased and sold annually as a result of the price advantage. Reliable used car price forecasting became essential to understand the vehicle's value and gained popularity. This involves many factors such as make, model, condition, and other features of the used car. These attributes are to be properly processed to get accurate predictions. This work's main goal is to estimate used automobile prices utilizing factors that have a significant impact on the price. Null, redundant, and missing values are found and processed using data mining techniques. These values should be eliminated, and significant qualities should be taken into account. Three regressors—the Random Forest Regressor, the Linear Regression, and the Bagging Regressor—are assessed, trained, and contrasted in this supervised learning study utilizing a benchmark dataset. The Random Forest Regressor scored the highest (95%), followed by the MAE (0.0008), RMSE (0.0378), and MSE (0.025) among all the experiments. Apart from Random Forest Regression, Bagging Regression also fared well, scoring 88%, and Linear Regression, scoring 85%. All studies employed an 80/20 train-test split with 40 random states. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Implementation of Cross Layer Design with Localization Techniques in Wireless Sensor Networks Using Deep Learning 4

Implementation of Cross Layer Design with Localization Techn...

引用

4th International Conference on Expert Clouds and Applications, ICOECA 2024

作者： Sreethar, S. Srinivas, Regulavalasa Satya S Chanakyan, C. Prasath, S. Senthilkumar, G. Natrayan, L. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Tamil Nadu Chennai India MVJ College of Engineering Department of Mechanical Engineering Karnataka Bengaluru India Mohamed Sathak A J college of Engineering Department of Mechanical Engineering Tamil Nadu Chennai India Panimalar Engineering College Department of Computer Science and Engineering Tamil Nadu Poonamallee Chennai India Saveetha School of Engineering SIMATS Department of Mechanical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350385793

This study addresses the integration of wireless sensor networks, machine learning models, and go-layer architecture to embellish industrial processes in small-scale manufacturing. A strong monitoring infrastructure is produced by the incorporation of various sensors, proximity, temperature, pressure, vibration, UWB, and RFID. Cross-layer arrangement, along with localization methodologies, gives spatial context to sensor information, enhancing safety, predictive maintenance, and asset monitoring. K-Nearest Neighbors (KNN), Recurrent Neural Networks (RNN), Artificial Neural Networks (ANN), and Decision Trees (DT) act as predictive models, exhibiting outstanding overall performance across accuracy, precision, keep in mind, and F1 Score criteria. Practical deployment in a small-scale firm, displaying CNC machines and forging stations, illustrates the machine's versatility. Results suggest the models' success in forecasting replies relying completely on dynamic sensor data, allowing actual-time selection-making. The system's usefulness supports enhanced safety measures, simpler maintenance processes, and optimal asset management. In addition to offering practical insights to organisations navigating the challenges of Industry 4.0, this research adds to the theoretical framework of move-layer layout and machine learning integration. The suggested system emerges as a complete solution for intelligent operational improvement and performance in modern day industrial settings. © 2024 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

A PAC-Bayesian Framework for Optimal Control with Stability Guarantees 63

A PAC-Bayesian Framework for Optimal Control with Stability ...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Boroujeni, Mahrokh Ghoddousi Galimberti, Clara LucIa Krause, Andreas Ferrari-Trecate, Giancarlo Institute of Mechanical Engineering Epfl Switzerland Eth Zϋrich Department of Computer Science Switzerland

ISBN: (纸本)9798350316339

Stochastic Nonlinear Optimal Control (SNOC) involves minimizing a cost function that averages out the random uncertainties affecting the dynamics of nonlinear systems. For tractability reasons, this problem is typically addressed by minimizing an empirical cost, which represents the average cost across a finite dataset of sampled disturbances. However, this approach raises the challenge of quantifying the control performance against out-of-sample uncertainties. Particularly, in scenarios where the training dataset is small, SNOC policies are prone to overfitting, resulting in significant discrepancies between the empirical cost and the true cost, i.e., the average SNOC cost incurred during control deployment. Therefore, establishing generalization bounds on the true cost is crucial for ensuring reliability in real-world applications. In this paper, we introduce a novel approach that leverages PAC-Bayes theory to provide rigorous generalization bounds for SNOC. Based on these bounds, we propose a new method for designing optimal controllers, offering a principled way to incorporate prior knowledge into the synthesis process, which aids in improving the control policy and mitigating overfitting. Furthermore, by leveraging recent parametrizations of stabilizing controllers for nonlinear systems, our framework inherently ensures closedloop stability. The effectiveness of our proposed method in incorporating prior knowledge and combating overfitting is shown by designing neural network controllers for tasks in cooperative robotics. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

EDU-GAN:Edge Enhancement Generative Adversarial Networks with Dual-Domain Discriminators for Inscription Images Denoising

引用

computers, Materials & Continua 2024年第7期80卷 1633-1653页

作者： Yunjing Liu Erhu Zhang Jingjing Wang Guangfeng Lin Jinghong Duan School of Mechanical and Precision Instrument Engineering Xi’an University of TechnologyXi’an710048China Department of Information Science Xi’an University of TechnologyXi’an710054China School of Faculty of Painting Packaging Engineering and Digital MediaXi’an University of TechnologyXi’an710048China School of Computer Science and Engineering Xi’an University of TechnologyXi’an710048China

Recovering high-quality inscription images from unknown and complex inscription noisy images is a challenging research *** fromnatural images,character images pay more attention to stroke ***,existingmodelsmainly consider pixel-level informationwhile ignoring structural information of the character,such as its edge and glyph,resulting in reconstructed images with mottled local structure and character *** solve these problems,we propose a novel generative adversarial network(GAN)framework based on an edge-guided generator and a discriminator constructed by a dual-domain U-Net framework,i.e.,*** existing frameworks,the generator introduces the edge extractionmodule,guiding it into the denoising process through the attention mechanism,which maintains the edge detail of the restored inscription ***,a dual-domain U-Net-based discriminator is proposed to learn the global and local discrepancy between the denoised and the label images in both image and morphological domains,which is helpful to blind denoising *** proposed dual-domain discriminator and generator for adversarial training can reduce local artifacts and keep the denoised character structure *** to the lack of a real-inscription image,we built the real-inscription dataset to provide an effective benchmark for studying inscription image *** experimental results show the superiority of our method both in the synthetic and real-inscription datasets.

关键词： Dual-domain discriminators inscription images denoising edge-guided generator

来源：评论

学校读者我要写书评

暂无评论

Numerical Predictions of Laminar Forced Convection Heat Transfer with and without Buoyancy Effects from an Isothermal Horizontal Flat Plate to Supercritical Nitrogen

引用

Frontiers in Heat and Mass Transfer 2024年第3期22卷 889-917页

作者： K.S.Rajendra Prasad Sathya Sai T.R.Seetharam Adithya Garimella Department of Mechanical and Industrial Engineering Manipal Institute of Technology BengaluruManipal Academy of Higher EducationManipal576104India Sustainable Energy Technology Faculty of Electrical EngineeringMathematics and Computer ScienceDelft University of TechnologyDelft2600 AANetherlands Department of Mechanical Engineering PES UniversityBengaluru560085India

Numerical predictions are made for Laminar Forced convection heat transfer with and without buoyancy effects for Supercritical Nitrogen flowing over an isothermal horizontal flat plate with a heated surface facing *** are performed by varying the value ofΔT from5 to 30 K and P_(∞)/P_(cr)ratio from1.1 to *** of all the thermophysical properties of supercritical Nitrogen is *** wall temperatures are chosen in such a way that two values of Tw are less than T∗(T*is the temperature at which the fluid has a maximum value of Cp for the given pressure),one value equal to T∗and two values greater than T∗.Three different values of U∞are used to obtain Re∞range of 3.6×10_(4)to 4.74×10^(5)for forced convection without buoyancy effects and Gr_(∞)/Re^(2)_(∞)range of 0.011 to 3.107 for the case where buoyancy effects are *** different forms of correlations are proposed based on numerical predictions and are compared with actual numerical *** has been found that in all six forms of correlations,the maximum deviations are found to occur in those cases where the pseudocritical temperature TT∗lies between the wall temperature and bulk fluid temperature.

关键词： Supercritical nitrogen laminar flow numerical methods forced convection heat transfer isothermal horizontal surface

来源：评论

学校读者我要写书评

暂无评论

Out-of-Distribution Detection Algorithms for Robust Insect Classification

引用

Plant Phenomics 2024年第2期6卷 433-444页

作者： Mojdeh Saadati Aditya Balu Shivani Chiranjeevi Talukder Zaki Jubery Asheesh K.Singh Soumik Sarkar Arti Singh Baskar Ganapathysubramanian Department of Computer Science Iowa State UniversityAmesIAUSA Department of Mechanical Engineering Iowa State UniversityAmesIAUSA Department of Agronomy Iowa State UniversityAmesIAUSA

Plants encounter a variety of beneficial and harmful insects during their growth *** identification(i.e.,detecting insects'presence)and classification(i.e.,determining the type or class)of these insect species is critical for implementing prompt and suitable mitigation *** timely actions carry substantial economic and environmental *** learning-based approaches have produced models with good insect classification *** aim to implement identification and classification models in agriculture,facing challenges when input images markedly deviate from the training distribution(e.g.,images like vehicles,humans,or a blurred image or insect class that is not yet trained on).

关键词： distribution robust detection algorithms classification insect

来源：评论

学校读者我要写书评

暂无评论

Warehouse Drone Inventory Management System Using OpenCV 25

Warehouse Drone Inventory Management System Using OpenCV

引用

25th International Seminar on Intelligent Technology and Its Applications, ISITIA 2024

作者： Afandi, Muzakki Dewi, Tiara Kusuma Widianingrum, Sinta Farizki, Muhammad Aldrifa Athhar Endrasari, Fitri Saptaji, Kushendarsyah Hadisujoto, Ignatius Budi Sutanto Djamari, Djati Wibowo Sampoerna University Computer Science Jakarta Indonesia Sampoerna University Mechanical Engineering Jakarta Indonesia

ISBN: (纸本)9798350378573

This research investigates the application of drone technology for enhancing inventory management efficiency. Utilizing DJI Tello Drones with integrated cameras, controlled via a Wi-Fi connection, and supported by OpenCV software on a PC, this study evaluates the effectiveness of drones in capturing and processing warehouse inventory data. The captured video feeds are analyzed for detection and recognition, with the results integrated into a real-time database. The study uses three ranges of 20 m, 50 m, and 100 m for the distance between the drone and the receiver device to analyze the distance factor affecting the latency. It is found that lower range between the drone and the receiver device results in better latency level. The experiment is conducted using the 20m distance for reduced latency. Experimental results demonstrate that drones can significantly reduce the time required for inventory tasks, with a recorded time of 2 minutes to document 16 items, compared to 15 minutes for manual checks. Additionally, the drones maintained a high detection accuracy, with an average successful detection distance of 0.55 meters for 8x8 cm QR codes. These findings substantiate the potential of drones and computer vision technology to optimize warehouse operations and supply chain management by increasing inventory accuracy, reducing labor costs, and improving responsiveness. This research contributes to the advancement of drone-enabled solutions across various industries, offering a pathway towards more efficient and agile inventory management practices. © 2024 IEEE.

关键词： Inventory control

来源：评论

学校读者我要写书评

暂无评论

Adaptive solar power generation forecasting using enhanced neural network with weather modulation

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 10955-10968页

作者： Sujeeth, T. Ramesh, C. Palwe, Sushila Ramu, Gandikota Basha, Shaik Johny Upadhyay, Deepak Chanthirasekaran, K. Sivasankari, K. Rajaram, A. Department of CSE Siddartha Educational Academy Group of Institutions Andhra Pradesh Tirupati India Department of Mechanical Engineering M. Kumarasamy College of Engineering Karur India Department of Computer Engineering and Technology MIT-WPU Maharashtra India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Telangana Hyderabad India Andhra Pradesh Mylavaram India Department of Computer Science and Engineering Graphic Era hill univeristy Dehradun India Department of Electronics and Communication Engineering Saveetha Engineering College Chennai India Department of Electronics and Communication Engineering Akshaya College of Engineering and Technology Coimbatore India Department of Electronics and Communication Engineering E.G.S. Pillay Engineering College Nagapattinam India

Solar power generation forecasting plays a vital role in optimizing grid management and stability, particularly in renewable energy-integrated power systems. This research paper presents a comprehensive study on solar power generation forecasting, evaluating traditional and advanced machine learning methods, including ARIMA, Exponential Smoothing, Support Vector Regression, Random Forest, Gradient Boosting, and Physics-based Models. Moreover, we propose an innovative Enhanced Artificial Neural Network (ANN) model, which incorporates Weather Modulation and Leveraging Prior Forecasts to enhance prediction accuracy. The proposed model is evaluated using real-world solar power generation data, and the results demonstrate its superior performance compared to traditional methods and other machine learning approaches. The Enhanced ANN model achieves an impressive Root Mean Square Error (RMSE) of 0.116 and a Mean Absolute Percentage Error (MAPE) of 36.26%. The integration of Weather Modulation allows the model to adapt to changing weather conditions, ensuring reliable forecasts even during adverse scenarios. Leveraging Prior Forecasts enables the model to capture short-term trends, reducing forecasting errors arising from abrupt weather changes. The proposed Enhanced ANN model showcases its potential as a promising tool for precise and reliable solar power generation forecasting, contributing to the efficient integration of solar energy into the power grid and advancing sustainable energy practices. © 2024 – IOS Press.

关键词： Solar power generation

来源：评论

学校读者我要写书评

暂无评论

LoRA-MedSAM: Efficient Medical Image Segmentation 5th

LoRA-MedSAM: Efficient Medical Image Segmentation

引用

5th International Conference on Medical Imaging and computer Aided Diagnosis, MICAD 2024

作者： Hu, Jiamin Xu, Xuwei Zou, Zhenmin Department of Mechanical and Aerospace Engineering University of Manchester Manchester United Kingdom School of Electrical Engineering and Computer Science The University of Queensland Brisbane Australia

ISBN: (纸本)9789819638628

Medical image segmentation becomes increasingly important for identifying and delineating anatomical structures, diseases, and abnormalities within medical images. However, existing large pre-trained foundation models for medical image segmentation, such as MedSAM, are often limited by their substantial computing resource requirements when fine-tuned for specific tasks. This high computational burden hinders their deployment in real-world clinical scenarios where rapid model adaptation is crucial yet computing resources are typically constrained. To address the challenge, in this paper, we introduce LoRA-MedSAM, a highly efficient method for fine-tuning large pre-trained models on medical image segmentation tasks. In particular, we leverage the Low-Rank Adaptation technique to significantly expedite the fine-tuning process of MedSAM model while maintaining high performance. Extensive experiments on three widely adopted medical image segmentation datasets have demonstrated both the effectiveness and efficiency of our method. Specifically, LoRA-MedSAM drastically reduces the fine-tuning time by 22.7%, 14.8% and 29.4% while outperforming the vanilla MedSAM by 1.1%, 5.5% and 0.5% higher Dice Similarity Coefficient (DSC) on the AMOS, BTCV and MultiTalent datasets, respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Medical imaging

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：