检索结果-内蒙古大学图书馆

Preparation and Characterization of Hybrid Composite Polyethylene fibers: Novel Catalyst in Treatment of Medical Waste

引用

Journal of The Institution of Engineers (India): Series D 2024年第2期105卷 1101-1114页

作者： Vinod, B. Suresh, S. Reddy, S. Sunil Kumar Sudhakara, D. Department of Mechanical Engineering Siddharth Institute of Engineering & Technology Puttur India Department of Mechanical Engineering Siddartha Institute of Science and Technology Puttur India

This research examines a new approach to using medical waste as a raw material. There are two types of medical waste: hazardous and non-hazardous. More than 70% of medical waste is considered non-hazardous waste, obtained from crushing used Surgical face mask (SFM) and Surgical Gloves (SG) as reinforcement materials chosen in this study. Biocomposites are eco-friendly and developed from natural and medical waste, with comparable performance to their lightweight synthetic counterparts. The research aims to increase the strength and high-temperature utilization of the Polyethylene (PE) matrix by employing bio-waste as particle reinforcement. Five different fiber composites of 3–12% weight fractions of natural fiber (Glass/pine apple leaf fiber) and a constant 10% medical waste were fabricated using an injection molding process to regulate the polymer structure and determine its thermal conduct. The thermal and mechanical characteristics (such as tensile, flexural, and impact strength) were enhanced by the incorporation of fillers. Tribological characteristics like specific wear rate and coefficient of friction were analyzed. Adding 9% (GF/PLF) with 10% (SFM/SG) particles improve the wear and mechanical properties of the hybrid composite by 52%, respectively. Interfacial bonding between the matrix material and fillers can be enhanced by including waste particles from the medical sector. Most domestic and automobile sectors have replaced metal components with plastics nowadays. © The Institution of Engineers (India) 2023.

关键词： Morphology

来源：评论

学校读者我要写书评

暂无评论

Tribological and Mechanical Characteristics of Mg–Zn6.0–Y1.2–Zr0.2 alloy by SPS Technique: Natural and Agro-Waste Utilization

引用

Journal of Bio- and Tribo-Corrosion 2023年第1期9卷 1-16页

作者： Vinod, B. Suresh, S. Reddy, S. Sunil Kumar Sujith, K. Sai Department of Mechanical Engineering Siddharth Institute of Engineering & Technology Puttur India

In India, urban solid waste generation has risen over the last decade. The aspect of waste generation is a large amount of waste materials among all solid waste types. While using ash particles eliminates waste, it also contributes desirable qualities. In this research work, the effects of Himalayan nettle leaf ash (HNLA) and bean pod ash (BPA) with molybdenum trioxide (MoO3) on the ZWK611 (Mg–Zn6.0–Y1.2–Zr0.2) alloy is examined. The as-cast alloy exhibits an α-Mg matrix, and cubic γ-phases are formed in addition to MoO3 particles. In this work, an attempt was made to choose a ZWK611 alloy reinforced with HNLA and BPA by varying weight percentages (X = 4, 8, 12, and 15%) with a constant weight percentage of MoO3 (5%) fabricated using spark plasma sintering (SPS) technique. The mechanical and physical properties were tested for both as-cast alloy and magnesium hybrid composites. Surface morphology and XRD are analysed to identify material behaviour. The addition of 12% (HNLA-BPA)/5%(MoO3) hybrid composite exhibits high strength as compared to the as-cast alloy. © 2022, The Author(s), under exclusive licence to Springer Nature Switzerland AG.

关键词： Morphology

来源：评论

学校读者我要写书评

暂无评论

Hybrid Filtering-Based Product Recommendation System Integrating GRU and BFGS Optimization

Hybrid Filtering-Based Product Recommendation System Integra...

引用

2024 IEEE International Conference on Electronic Systems and Intelligent Computing, ICESIC 2024

作者： Suresh, A. Kumar, R.G. Nagaraju, D. Mohana Sundaram, K.D. Anandan, B. Siddharth Institute of Engineering and Technology Department of Computer Science and Engineering Puttur India Siddharth Institute of Engineering and Technology Department of ECE Puttur India

ISBN: (纸本)9798331522988

It is more crucial than ever to handle crucial problems including data sparsity, cold-start problems, and the requirement for extremely precise forecasts in today's ever changing recommendation system field. This work presents a hybrid filtering product recommendation system that integrates Gated Recurrent Units (GRU) with the Broyden-Fletcher-Goldfarb-Shanno (BFGS) optimization method to significantly enhance recommendation accuracy and performance. Standard techniques such content-based filtering and collaborative filtering can fail to offer reliable recommendations for large and dynamic datasets. Our hybrid model uses BFGS optimization to increase model accuracy and efficiency while utilizing GRU-based collaborative filtering to capture sequential user-item interactions. The GRU-BFGS model outperforms matrix factorization (MF) techniques in numerous areas, achieving an astounding accuracy of up to 92% on the Amazon customer review dataset. It also exhibits excellent recall, precision, and notable decreases in error metrics (MAE, MSE, and RMSE), which makes it a very successful method for providing individualized, accurate suggestions. © 2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Enhancement of Dynamic and Tribological Characteristics of Epoxy Coating: Eco-friendly and Noval Biodegradable Fillers into Raw Materials

引用

Journal of Bio- and Tribo-Corrosion 2024年第2期10卷 1-18页

作者： Vinod, B. Raju, F. Anand Elaiyarasan, U. Suresh, S. Department of Mechanical Engineering Siddharth Institute of Engineering & ampTechnology Puttur India Department of Automobile Engineering Easwari Engineering College Chennai India

This research examines agricultural wastes that can be used as natural fiber reinforcement in polymer composites. The experiments are conducted with two different mixtures of fiber ratios and with/without coating composites. In the primary mix, three varieties of fibers (Tea leaf, pineapple leaf, and spinifex littoreus) were induced as reinforcement materials in the epoxy matrix. Fibers are abundantly available as agricultural residues in India. A constant 20% silica, consisting of phenolic compounds acting as antioxidants, is added to the reinforcement. It helps improve flammability behavior. MoS2 dip coating is performed on hybrid fibers in the secondary mixture. The research focuses on the before and after dip coating of MoS2 powder material used as an additive to improve tribological and mechanical properties. The tribological properties are identified as varying load, distance, and velocity. The results show that the fiber ratios mainly influence the thermo-mechanical properties, and the MoS2 coating influences the tribology properties of hybrid fiber-reinforced composites. OM analysis is used to examine the fractography behavior of coated samples. Adding 4% (TLF/PLF/SLF) with 20% silica dip-coated material improves the wear properties of the CFRHC2 by 21%, respectively. The high flexural and impact strength achieved compared to the epoxy matrix is 12.32 MPa and 37.3 kJ/m2. This material is suitable for manufacturing products, such as table tennis racquets, writing pads, trays, and switchboards. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Dip coating

来源：评论

学校读者我要写书评

暂无评论

Detection of Parkinson's Disease using Machine Learning with Feature Analysis from Audio Signals 4

Detection of Parkinson's Disease using Machine Learning with...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Purnima, Kuruma Manivasagam, M.A. Kaif, Dudekula Mohammed Vanitha, M. Rajesh, Nagella Silambarasan, B. Suhail, Shaik Kumar, G. Ravi Rao, V. Hanumantha Siddharth Institute of Engineering & Technology Department of Cse Puttur India Siddharth Institute of Science & Technology Department of Cse Puttur India

ISBN: (纸本)9798350352931

Background: Early detection of Parkinson's Disease (PD) is crucial for timely intervention and improved patient outcomes. PD affects motor functions and often results in vocal impairments, making voice analysis a promising non-invasive diagnostic approach. Methods: This study evaluates the effectiveness of machine learning algorithms - Decision Tree, Random Forest, Logistic Regression, Support Vector Machine, Naive Bayes, K-Nearest Neighbors, and XGBoost - for PD detection using a dataset of vocal features from the UCI Machine Learning Repository. The dataset, comprising 23 vocal attributes, was preprocessed using the Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance. Models were assessed using metrics such as Accuracy, F1-Score, Recall, Precision, and ROC-AUC. Results: The Random Forest and Support Vector Machine algorithms demonstrated the highest classification accuracy (96.6%) and superior overall performance. These findings highlight the potential of these methods for distinguishing between PD-positive and PD-negative cases using voice data. Concluding Remarks: This study underscores the potential of machine learning in developing accessible and accurate tools for early PD diagnosis. Further enhancements, such as feature refinement and dataset expansion, could improve these methods' generalizability and robustness, supporting their integration into healthcare systems. © 2024 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Secure and Efficient Deduplication for Multimedia Sharing in Privacy-Sensitive Cloud Ecosystems 3

Secure and Efficient Deduplication for Multimedia Sharing in...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Suresh, A. Murali, Erasappa Anjali Sri, V. Sumana, E. Sathwik, Gopaluni Venkata Sai Devendra Reddy, P. Department of Computer Science and Engineering Siddharth Institute of Engineering & Technology Puttur India

ISBN: (纸本)9798331527549

Current cloud-based systems face the challenge of managing storage and eliminating redundant data associated with the exponentially growing multimedia content, where numerous semantically similar but nonidentical files are included. In this paper we introduce a novel secure deduplication framework for encrypted cloud storage. This proposed system employs similarity-preserving hashing, fuzzy PoW protocol, and attribute-based encryption to perform efficient deduplication without compromising security and providing ownership verification. Security and deduplication rate scalability are improved over brute-force and ownership-faking attacks by dynamically varying thresholds based on file characteristics. Experimental evaluation shows that a 48% average deduplication rate and resistance to common attack vectors make it suitable for real-world cloud storage scenarios. The framework fills critical gaps in existing approaches and provides an innovative solution for dealing with similarity-aware data deduplication in privacy-sensitive environments. © 2025 IEEE.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

Empowering Fake News Detection Through Innovative Hybrid Deep Learning-Based Approach

Empowering Fake News Detection Through Innovative Hybrid Dee...

引用

2025 International Conference on Computing for Sustainability and Intelligent Future, COMP-SIF 2025

作者： Suresh, A. Mallika, R.M. Gireesh, S. Singh, G. Hari Kiran Jeevanandham, E.S. Hemalatha, A. Siddharth Institute of Engineering & Technology Department of Computer Science and Engineering Puttur India Puttur India

ISBN: (纸本)9798331538538

The essence of getting information to the populace in the shortest time possible through social media and other interactive technologies has made it easier for fake news to thrive hence creating a menace to any society as well as its decision-making systems. This research work presents a sound AI-based approach to classify fake news using DL algorithms embedded within a CNN-BiLSTM model. Using the ISOT dataset, the comparison of the outcomes achieved by the proposed model with the original models shows that the proposed model has the highest accuracy score of 94.07%, a precision of 93.50%, a recall of 94.60%, and an F1-score of 94.00%. The proposed hybrid model architecture of CNN for spatial feature extraction and BiLSTM for capturing contextual dependencies that are essential for text analysis and have relatively high accuracy compared to conventional ML algorithms, including CNN, RNN, LSTM, and other DL methods. The proposed approach is verified by a set of comprehensive measures, including ROC curve analysis and various training-validation metrics that reveal the effectiveness of the presented approach in overcoming the challenges of fake news identification. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Characterization of high-strength concrete by Preferential supplant of scrap tyre rubber powder-bambara nut shell ash constituent: utilization of novel waste materials in concrete

引用

Journal of Building Pathology and Rehabilitation 2023年第1期8卷 1-14页

作者： Reddy, K. Chandrasekhar Hemadri, G. Department of Civil Engineering Siddharth Institute of Engineering & Technology Puttur India

Concrete is an artificial matrix with water, cement, and fine and coarse aggregates. Adding mineral admixtures and waste materials to concrete has evolved into a spectacular achievement nowadays. The current investigation replaces cement with mineral admixtures such as silica fume (SF) and ground granulated blast-furnace slag (GGBS). Scrap Tyre Rubber Powder (STRP) and Bambara Nut Shell Ash (BNSA) are two regionally significant waste materials used to replace fine aggregates. The workability, strength, and durability of M25 grade concrete were determined using concrete specimens at a constant replacement of cement by 10% of SF and 20% of GGBS, and fine aggregate partial replacement at 5%, 10%, 15%, and 20% of STRP and BNSA. The workability of green concrete, compressive, flexural, and splitting tensile strengths at 7, 14, and 28 days of curing and durability (sulphate attack) at 90 days of curing were conducted and correlated with conventional concrete. Test results showed the concrete performed better at partially replacing the cement with 30% admixture (SF-GGBS) and fine aggregate with 15% waste material (STRP-BNSA). The workability improved by 12.24% (slump) and 8.89% (compaction factor), and the gain in concrete strength at 28 days was 21.04% (compressive) and 18.34% (splitting tensile) than conventional mix. © 2022, The Author(s), under exclusive licence to Springer Nature Switzerland AG.

关键词： Durable properties Ground granulated blast-furnace slag Particle size distribution Scrap tyre rubber powder Silica fume

来源：评论

学校读者我要写书评

暂无评论

Detection Of Phishing Attacks Based On Url By Using Machine Learning 10

Detection Of Phishing Attacks Based On Url By Using Machine ...

引用

10th International Conference on Electrical Energy Systems, ICEES 2024

作者： Mekalarani, T.M.S. Subhasree, R.S. Reddy, R. Thrisha Chandini, Shaik Kumar, Yadhallapalle Satheesh Valli Shaik, Ashraf Siddharth Institute of Engineering & Technology Department of Computer Science and Engineering Andhra Pradesh India

ISBN: (纸本)9798350353778

Phishing, a cybercrime orchestrated by intruders or hackers, aims at duping unsuspecting individuals into revealing sensitive information via deceptive websites. The primary objective of this nefarious activity is to obtain personal or classified data from victims, which can then be exploited for diverse purposes. The stolen information, often sold in online black markets, commands varying prices based on its importance, ranging from a few dollars to thousands. Techniques like machine learning (ML) and deep learning (DL) offer strong instruments for analyzing and thwarting such complex threats. The project aims to protect users and websites from these impending risks by putting forth a machine learning-based phishing detection system. Drawing upon a URL-based dataset sourced from a reputable repository, encompassing attributes from both phishing and legitimate URLs from over eleven thousand websites, the process involves several preprocessing stages. Later, other machine learning methods are used, including Random Forest and Decision Trees, combined to build a strong detection model. To enhance efficacy, the system integrates TF-IDF values of webpages, resulting in superior accuracy compared to prior methodologies. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Enhance the Context-Based Online Recommendation System using Deep Reccurrent Neural Network with Enhaned Pigeon Search Optimization

Enhance the Context-Based Online Recommendation System using...

引用

2024 IEEE International Conference on Recent Advances in Science and engineering technology, ICRASET 2024

作者： Suresh, A. Sridhar, J. Mallika, R.M. Nagaraju, D. Indiravathi, G. Siddharth Institute of Engineering & Technology Dept of Cse AP Puttur India

ISBN: (纸本)9798350388602

Most research in the area of Recommendation Systems (RS) seeks to improve quality by applying multiple methodologies. The main objective is to improve predictive performance while disregarding other design objectives, including the environment of a patient's article. As a result, at numerous levels, a learning-based RS was proposed in this research. It is an efficient RS to improve the smallest amount of error during suggestion. The information started with the Python framework. Following preprocessing, the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm was used to present the extracted and contextual information from each preprocessing evaluation. The resulting characteristics were used as an entry for density-based clustering, which groups client evaluations into negative, neutral and favourable attitudes. Each item had an uncertain chance of being appreciated by a customer. The effectiveness of the recommendation system was measured according to its regrets, using an Oracle method that would know the probability of a benchmark. The hybrid Deep Recurring Neural Network- Enhanced Pigeon Search Optimization (DRNN-EPSO) method has been used to initialize the Recurrent Neural Network (RNN) modeling input variables. Also, the article used RNN, logistic regression, Multi-Layer Perceptron (MLP) and other supervised learning methods. Our study indicates the weighting factor of the various components of disappointment (i) the element emerging from the restriction of not trying to present the very same product to the very same consumer 2 times, (ii) the element emerging from having to learn the opportunities consumers like goods, & lastly the element emerging from having to learn the internal structure. The proposed model's performance was measured using correctness, specificity, & recall measures, and it is contrasted latest systems. The proposed model has an average accuracy of 99.6%, which would be more accurate than previous machine learning techniques. ©

关键词： Deep neural networks

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：