检索结果-内蒙古大学图书馆

Comparison of the Performance of Groundnut Shell-Based Carbon-Reinforced PLA Composites, Fabricated using Injection Molding and Pellet 3D Printing

引用

Archives of Metallurgy and Materials 2025年第1期70卷 127-134页

作者： Radhika, M. Anjaneya Prasad, B. Akella, Suresh Jawaharlal Technological University Telangana Hyderabad India Vignan Institute of Technology and Science Deshmukhi Telangana Hyderabad India Sreyas Institute of Engineering and Technology Naderagul Telangana Hyderabad India

This study intended to investigate the impact of two distinct shaping methods, Injection molding and pellet additive manufacturing, on tensile and thermal properties of PLA based materials. It included comparisons of neat PLA and PLA reinforced with carbon nanoparticles derived from groundnut shells (GNSC) via pyrolysis at 800°C. These nanoparticles were characterized using FTIR, XRD, FESEM, and EDX analyses to assess their carbon content, morphology, and structure. The synthesized carbon was used as a reinforcement filler in the PLA matrix and biobased polymer nanocomposites were prepared by pellet 3D printing and injection molding. The mechanical and thermal characteristics of PLA/GNSC composite specimens with 0.25, 0.5, and 0.75 wt% of GNSC nanoparticles were compared. Reinforcing PLA with GNSC nanoparticles improved tensile properties in both shaping techniques. The PLA/GNSC_0.5 exhibited the greatest tensile strength, measuring 58.61 MPa for injection molded samples and 53.05 MPa for 3D printed samples, representing a 50% enhancement compared with neat PLA. The tensile modulus was also highest for PLA/GNSC_0.5, measuring 1.24 GPa for injection molded samples and 1.21 GPa for 3D printed samples, representing an improvement of 14% compared with neat PLA. The tensile characteristics showed a modest increase in tensile strength (9-13%) and a slight improvement in tensile modulus (2-3%) for injection molded samples compared to 3D printed samples. The thermal properties showed no substantial variation between the two shaping methods. These findings highlight the effectiveness of GNSC nanoparticles in enhancing the mechanical and thermal performance of PLA composites, regardless of the shaping technique. © 2025. The Author(s).

关键词： Tensile strength

来源：评论

学校读者我要写书评

暂无评论

Enhancing the mechanical properties of 3D-Printed polylactic acid through pellet additive manufacturing: A grey relational analysis based on entropy weights

引用

International Journal of Lightweight Materials and Manufacture 2025年第3期8卷 331-340页

作者： Mandala, Radhika Prasad, B. Anjaneya Akella, Suresh Jawaharlal Nehru Technological University Hyderabad Kukatpally Telangana Hyderabad India Vignan Institute of Technology and Science Deshmukhi Telangana Hyderabad India Sreyas Institute of Engineering and Technology Naderagul Telangana Hyderabad India

The most prevalent and extensively employed additive manufacturing (AM) approach method is fused deposition modeling (FDM), which uses filament as feedstock. Pellet additive manufacturing (PAM) is an emerging technique within the field of FDM that utilizes thermoplastic pellets as the feedstock considering their greater ease of production compared to filaments. The PAM technique enables the production of intricate components with high dimensional precision and cost efficiency by eliminating the need to transform pellets into filaments. The discreet choice of printing parameters greatly influences the performance of 3D-printed objects. This work underscores the significance of printing parameters on mechanical performance measures, tensile, flexure, and hardness characteristics by utilizing a multi-objective optimization technique. It is a combination of the Taguchi, analysis of variance (ANOVA), and entropy-based grey relational analysis (EGRA). A Taguchi L9 orthogonal array is employed, with infill pattern, raster angle, and layer height as the control variables, while tensile and flexural strengths, and hardness serve as the output responses. The findings demonstrated that the optimum outcomes were achieved for the gyroid infill pattern at 45° orientation and 0.25 mm layer height. Enforcing EGRA in multi-objective optimization has resulted in an improvement of 3.3 % in the grey relational grade when compared to the initial parameter configurations. Hence, EGRA proves to be an effective potential tool for the optimization process in PAM. © 2025 The Authors

关键词： Feedstocks

来源：评论

学校读者我要写书评

暂无评论

Triangular Groove Effect on Heat and Mass Transfer of CuO-Water Nanofluid Through a Square Channel

引用

International Journal of Applied and Computational Mathematics 2025年第2期11卷 1-22页

作者： Baradi, Lavanya Srinivas, G. Babu, B. Suresh Department of Mathematics BEST Innovation University Andhra Pradesh Gownivaripalli Gorantla India Department of Mathematics St. Francis College for Women Begumpet Hyderabad India Department of Mathematics Geethanjali College of Engineering and Technology Hyderabad India Department of Mathematics Sreyas Institute of Engineering and Technology Hyderabad India

The pipes used in heat exchangers are of circular, square, etc., cross-sectional shapes. But the heat transfer depends on the surface area of the source or sink. So the regular cross-sectional shapes are most common, but the heating through a projection into the fluid certainly affects characteristics of the heat and mass transfer. This study investigates the turbulent flow heat and mass transfer characteristics of CuO–water nanofluid in a square channel with an inner triangular groove that is continuously heated. By applying a transverse magnetic field, the governing coupled and nonlinear equations are solved using the Galerkin finite element method across various flow regimes, including laminar, transitional, and turbulent flows. The analysis provides comprehensive insights into the effects of different parameters through stream plots and contour plots. The heat transfer rate, represented by the Nusselt number (Nu), is graphically presented for the heated inner triangular groove and thoroughly discussed. The novel results of the study are that the heat transfer rate increases by 5% with the inclusion of 3% metal in the base fluid. To achieve this, the Reynolds number has to be preferred around 100;also, the heat transfer rate enhances by 15–20% when Nb = Nt = 1.6. © The Author(s), under exclusive licence to Springer Nature India Private Limited 2025.

关键词： CuO-water nanofluid Finite element method Inner triangular groove Square horizontal channel Turbulent and transitional flow

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation of Areal Images using Pixel Wise Segmentation

引用

Procedia Computer Science 2025年 259卷 463-472页

作者： Swathi Gowroju V. Swathi Narsimhulu K. Shilpa Choudhary Associate Professor Department of Artificial Intelligence & Machine Learning Sreyas Institute of Engineering and Technology Hyderabad Telangana Assistant Professor Department of Computer Science Sreyas Institute of Engineering and Technology Hyderabad Telangana Assistant Professor Department of Computer Science Matrusri Engineering College Hyderabad Telangana Associate Professor Department of Computer Science NGIT Hyderabad Telangana

Particularly in regions hit by flooding, precise semantic segmentation of aerial photographs is essential for post-disaster evaluation and urban planning. The high-resolution aerial photography collection FloodNet, created for pixel-by-pixel segmentation of flooded and non-flooded landscapes, is presented in this work. Aerial photos taken from various geographic regions make up the collection, and segmentation masks are used to detect flooded roads, houses, cars, plants, and other vital infrastructure. In order to conduct semantic segmentation on aerial photos and capture the fine-grained information necessary for flood damage assessments, the suggested model makes use of a U-Net architecture. Morphological post-processing is also used to improve object delineation and smooth segmentation borders. The model showed consistent performance with little overfitting, achieving training accuracy of 84% and validation accuracy of 81% over 200 epochs. Effective generalization to unknown data was demonstrated by the validation loss stabilizing at 0.55 and the training loss declining from 1.1 to 0.45. The findings show that the suggested method can reliably identify and categorize areas damaged by flooding from aerial photos, enabling automated flood assessment and speeding up disaster relief activities. There is a lot of promise for integrating this model and dataset combination into real-time catastrophe monitoring, urban planning, and geospatial analytic pipelines.

关键词： Satellite images areal images semantic segmentation UNet using morphology Pixel wise segmentation

来源：评论

学校读者我要写书评

暂无评论

Blockchain for Machine Learning: Security and Trust in Data Sharing

Blockchain for Machine Learning: Security and Trust in Data ...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Kiran, G Ravi Maisaiah, Nakka Divya, T.V. Reddy, G V Subba Petikam, Sailaja Sharma, M.K. Sr University School of Cs & Ai Telangana Warangal India Mahaveer Institute of Science and Technology Department of Information Technology Telangana Hyderabad500005 India Sreyas Institute of Engineering and Technology Department of Cse Telangana Hyderabad500068 India Siddhartha Institute of Technology and Science Ece Department Hyderabad India Simats Saveetha School of Law Chennai600077 India Mathematics Chaudhary Charan Singh University Uttar Pradesh Meerut250004 India

ISBN: (纸本)9798331508685

Data security has become the most important things in this current digitalized environment. As in this era, each process leaves a digital footprint and it requires significant monitoring to maintain trust of stakeholders. It necessitates the companies to evaluate their necessary information including the sensitive and confidential data as per their requirements while maintaining data security and customers' trustworthiness. While managing data security, companies require limited accessibility of their confidential business information. Personal and private information are the most commonly targeted dataset for hackers in this technological age. Since ML is efficient in evaluating huge datasets, companies must prioritize the potential security concerns. To use artificial intelligence (AI) and ML-driven technologies widely, blockchain has become significant to develop faith among the stakeholders. The research evaluates the efficiency of blockchain technology in improving data security while suggesting its integration with ML-based business approaches. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Micro-Expression Recognition Through Graph Convolutional Networks and Metric Learning

引用

Journal of Shanghai Jiaotong University (Science) 2025年 1-14页

作者： Bhukya, Sreenivasu Devi, L. Nirmala Rao, A. Nageswar Department of ECE Sreyas Institute of Engineering and Technology Telangana Hyderabad500068 India Department of ECE University College of Engineering Osmania University Telangana Hyderabad500007 India Strategic Electronics Research and Design Center Hindustan Aeronautics Limited Telangana Hyderabad500042 India

Micro-expression recognition (MER) remains a challenging task due to the subtle and transient nature of micro-expressions, which often results in poor generalization and low recognition accuracy in existing approaches. This research introduces a novel MER framework that integrates graph convolutional networks (GCNs) with facial action unit features to address critical limitations, including ineffective feature extraction, class imbalance, and insufficient temporal modeling. The proposed method effectively divides the facial region into seven anatomically significant areas, i.e., left eye, right eye, nose, lips, left cheek, right cheek, and chin, enabling precise localization of muscle movements associated with micro-expressions. Optical flow-based motion analysis is employed to extract temporal changes in facial pixels across video sequences, ensuring the capture of subtle dynamic patterns. To enhance spatial feature extraction, a graph-based connectivity matrix models relationships between facial regions, which are then processed using GCNs to learn spatial dependencies and muscle activation patterns. Feature centering and L2 normalization are applied to improve feature robustness and ensure consistent representation across varying datasets. Additionally, a novel metric learning-based prototype classifier is introduced to mitigate class imbalance by incorporating a loss function that penalizes misclassifications of minority classes, thereby improving recognition performance on underrepresented categories. The proposed method achieves state-of-the-art performance with recognition accuracies of 81.83% on the SMIC dataset, 87.83% on CASME, and 93.48% on CASME II, significantly surpassing existing methods. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

A comparative study of traditional machine learning models and the KNN-KFSC method for optimizing anomaly detection in VANETs

International Journal of Systematic Innovation

引用

International Journal of Systematic Innovation 2025年第2期9卷 37-46页

作者： Ch, Ravikumar Kavitha, D. Sowjanya C., S. Pallavi, S. Ramesh, Vankudoth Department of CSE Sreenidhi University Hyderabad India Department of CSE-AIML GNITS Shaikpet Hyderabad India Department of CSE Sreyas Institute of Engineering and Technology Hyderabad India Department of CSE GNITS Shaikpet Hyderabad India Department of Emerging Technologies CVR College of Engineering Hyderabad India

In this research, we conducted a comparative analysis of traditional machine learning techniques and the innovative K-nearest neighbors-K-fuzzy subspace clustering (KNN-KFSC) methodology to detect anomalies in vehicular ad hoc network (VANET) infrastructures. Our evaluation included models such as support vector machine (SVM), random forest (RF), logistic regression (LR), and KNN. The KNN-KFSC model demonstrated exceptional performance with an overall accuracy rate of 99% in handling densely contextual data. It consistently exhibited high accuracy, recall, and F1 score metrics, indicating its effectiveness in detecting a broad spectrum of anomalies across various types of attacks in VANETs. In contrast, the RF algorithm achieved an 89% accuracy rate, showcasing competency in specific domains but revealing limitations in others. Both LR and SVM models exhibited identical accuracy rates of 92%. While effective in identifying specific types of attackers, these models showed weaknesses, potentially due to overfitting or inadequate management of dataset complexity. The KNN-KFSC approach emerged as the most promising option for detecting anomalies in software-defined VANETs, evidenced by its superior performance in accuracy and precision. Our findings underscore the necessity of advanced intrusion detection system techniques and highlight the importance of model refinement to address data imbalances and improve anomaly detection in VANET systems. © (2025), (Society of Sytematic Innovation). All rights reserved.

关键词： Intrusion Detection KNN-KFSC Method Machine Learning VANET Vehicular Communication

来源：评论

学校读者我要写书评

暂无评论

Blockchain for Machine Learning: Security and Trust in Data Sharing

Blockchain for Machine Learning: Security and Trust in Data ...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： G Ravi Kiran Nakka Maisaiah T V Divya G V Subba Reddy Sailaja Petikam M. K. Sharma School of CS & AI SR University Warangal Telangana Department of Information Technology Mahaveer Institute of Science and Technology Hyderabad Telangana Department of CSE Sreyas Institute of Engineering and Technology Hyderabad Telangana ECE Department Siddhartha Institute of Technology and Science Hyderabad Saveetha School of Law SIMATS Chennai Mathematics Chaudhary Charan Singh University Meerut Uttar Pradesh India

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Data security has become the most important things in this current digitalized environment. As in this era, each process leaves a digital footprint and it requires significant monitoring to maintain trust of stakeholders. It necessitates the companies to evaluate their necessary information including the sensitive and confidential data as per their requirements while maintaining data security and customers’ trustworthiness. While managing data security, companies require limited accessibility of their confidential business information. Personal and private information are the most commonly targeted dataset for hackers in this technological age. Since ML is efficient in evaluating huge datasets, companies must prioritize the potential security concerns. To use artificial intelligence (AI) and ML-driven technologies widely, blockchain has become significant to develop faith among the stakeholders. The research evaluates the efficiency of blockchain technology in improving data security while suggesting its integration with ML-based business approaches.

关键词： Data security Voting Machine learning Companies Medical services Blockchains Stakeholders Monitoring Financial services Business

来源：评论

学校读者我要写书评

暂无评论

Advanced Deep Learning Techniques for Multivariate Weather Prediction Using RNN and LSTM Models

Advanced Deep Learning Techniques for Multivariate Weather P...

引用

Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), International Conference on

作者： Chintha Venkata Ramana B.Venkata Varma U. V. Ramesh P. Anand Kumar A. Lakshmanarao Raja Rao PB V Department of CSE Shri Vishnu Engineering College for Women Bhimavaram India Department of CSE Sreyas institute of engineering and Technology Telangana India Department of CSE Aditya University Surampalem India Department of CSE Jayamukhi Institute of Technological Sciences Warangal India Department of IT Aditya university Surampalem India Department of CSE Shri Vishnu Engineering College for Women (A) Bhimavaram Andhra Pradesh India

ISBN: (数字)9798350356236

ISBN: (纸本)9798350356243

This paper investigated advanced deep learning and traditional machine learning techniques for multivariate weather forecasting using time series data. A dataset with weather features like temperature, humidity, wind speed, and precipitation over extended periods of time was collected. Experiments were conducted with each feature of temperature, humidity, wind speed, and precipitation as the target variable to evaluate predictive accuracy in multiple scenarios. Initially, traditional machine learning regression models like Random Forest Regression (RFR), Decision Tree Regression (DTR), Gradient Boosted Regression (GBR), and Multiple Linear Regression (MLR) were applied as base models for predictive evaluation. Later, advanced deep learning models like RNN, LSTMs and GRU were applied and observed to enhance performance with respect to measures MSE, MAE, RMSE, and r-squared values. The results reveal the strengths of advanced methods over traditional ML models. This work contributes to valuable insights into weather forecast modeling.

关键词： Deep learning Precipitation Accuracy Wind speed Weather forecasting Humidity Predictive models Regression tree analysis Long short term memory Random forests

来源：评论

学校读者我要写书评

暂无评论

Numerical analysis on heat and mass transfer of immiscible fluids in a vertical channel with diffusion effects

引用

Partial Differential Equations in Applied Mathematics 2025年 13卷

作者： Kumaraswamy, P. Goud, T Ramakrishna Babu, B. Suresh Gosty, Vanaja Srinivas, G. Haripriya, T. Makinde, O.D. Dept. of Mathematics Geethanjali college of Engineering and Technology Hyderabad India Dept of Mathematics University College of Science Saifabad Hyderabad India Dept. of Mathematics Sreyas Institute of Engineering and Technology Hyderabad India Faculty of Military Science Stellenbosch University Private Bag X2 Saldanha 7395 South Africa

This research paper explores the intricacies of heat and mass transfer in a vertical channel with immiscible fluids, focusing on the dynamics of two-fluid flows under the influence of variable viscosity, thermal conductivity, and thermal slip. The study further incorporates the effects of an internal heat source, adding complexity to the analysis of transfer processes. Mathematica's ND Solve software implements the Runge-Kutta sixth-order method, ensuring precise numerical simulations. A comprehensive analysis is performed on dimensionless velocity, angular velocity, temperature, and diffusion across relevant parameters. The results are visually represented to derive significant insights, including the impact of heat source intensity on the flow and transfer mechanisms. Bar charts illustrate critical components, such as shear stress, the Sherwood number, and the Nusselt number, enabling a clear comparison of heat and mass transfer rates along the channel wall. These findings contribute valuable knowledge for optimizing heat and mass transfer in various engineering applications. © 2025 The Author(s)

关键词： Diffusion Effects Heat and mass transfer Thermal slip Two-fluid flows Variable conductivity Variable viscosity

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：