检索结果-内蒙古大学图书馆

Predicting biochar yield from biomass pyrolysis: A comprehensive data-driven approach using machine learning and SHAP analysis

引用

Results in engineering 2025年 26卷

作者： Walid Abdelfattah Munthar Kadhim Abosaoda Krunal Vaghela Gowrishankar J Prabhat Kumar Sahu Kamred Udham Singh R. Sivaranjani Rohit Chauhan Siya Singla Samim Sherzod Department of Mathematics College of Science Northern Border University Arar Saudi Arabia College of Pharmacy The Islamic University Najaf Iraq College of Pharmacy The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Marwadi University Research Center Department of Computer Engineering Faculty of Engineering & Technology Marwadi University Rajkot Gujarat India Assistant Professor Department of Computer Science Engineering School of Engineering and Technology JAIN (Deemed to be University) Bangalore Karnataka India Department of Computer Science and Information Technology Siksha 'O' Anusandhan (Deemed to be University) Bhubaneswar Odisha 751030 India School of Computing Graphic Era Hill University Dehradun India Adjunct Professor Centre for Promotion of Research Graphic Era Deemed to be University Dehradun Uttarakhand 248002 India Department of CSE Raghu Engineering College Visakhapatnam Andhra Pradesh 531162 India Department of Computer Application Chandigarh Engineering College Chandigarh Group of Colleges-Jhanjeri Mohali Punjab 140307 India Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Rajpura Punjab 140401 India Faculty of Engineering Nangarhar University Nangarhar Afghanistan

Biochar, a pivotal product of biomass pyrolysis, is crucial in sustainable agriculture, carbon sequestration, and renewable energy systems. This study employs a comprehensive data-driven approach to predict biochar yield using machine learning algorithms. The dataset, comprising 14 chemical, physical, and reaction parameters collected from reputable studies, was processed using outlier detection via the Monte Carlo Outlier Detection (MCOD) algorithm and hyperparameter tuning to optimize model performance. Among the evaluated models, the Decision Tree algorithm emerged as the most robust predictor, achieving an R² value of 0.771, a mean square error (MSE) of 16.182, and an average absolute relative error percentage (AARE%) of 11.848 % in testing. The SHAP analysis identified residence time, pyrolysis temperature, and ash content as the most influential predictors of biochar yield. Simplified explanations and interpretability offered by these models support their practical application. These findings underline the potential of machine learning to optimize biochar production, enhance agricultural systems, and create scalable methods for sustainable waste management, directly contributing to renewable energy and environmental remediation industries.

关键词： Biochar yield Machine learning Biomass pyrolysis Decision tree SHAP analysis

来源：评论

学校读者我要写书评

暂无评论

A deep learning approach for Indian sign language gestures classification with different backgrounds

引用

Journal of Physics: Conference Series 2021年第1期1950卷

作者： R. Dhiman G. Joshi C. Rama Krishna PG Scholar Department of Computer Science & Engineering NITTTR Chandigarh INDIA. Assistant Professor Department of Electronics & Communication Engineering UIET Panjab University Chandigarh INDIA Professor & Head Department of Computer Science & Engineering NITTTR Chandigarh INDIA.

The sign language recognition system recently has drawn the attention of various researchers as there is no universal sign language, moreover, it consists of many patterns and postures. Many methods for extracting features and classifying sign language have been proposed in the literature, most of them are based on machine learning techniques. In this article, a deep learning method has been adopted by designing a Convolution Neural Network (CNN) model to extract the sign language features where for classification softmax layer is used. All alphabets in simple as well as complex backgrounds have been considered, where data is collected from 100 subjects in different lighting conditions. The effect of various optimization techniques (Adam, Sgdm, RMSProp), activation functions (ReLU and Leaky ReLU) for generalization ability is also observed. The proposed approach has succeeded in attaining the testing accuracy of 99.10%, 92.69%, and 95.95% on the Indian sign language dataset with simple, complex backgrounds and on a mixed background scenarios, respectively. The model is also tested on NUS dataset-I, NUS dataset-II, their combination, and achieved the accuracy of 100%, 95.95%, and 97.22% respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Automated Optimize Utilization of Water and Crop Monitoring in Agriculture Using IoT

引用

IOP Conference Series: Materials science and engineering 2021年第1期1131卷

作者： Sanwta Ram Dogiwal Pankaj Dadheech Ankit Kumar Linesh Raja Abhishek Kumar Mahender Kumar Beniwal Associate Professor Department of Information Technology Swami Keshvanand Institute of Technology Management & Gramothan Jaipur Rajasthan India Associate Professor Department of Computer Science & Engineering Swami Keshvanand Institute of Technology Management & Gramothan Jaipur Rajasthan India Assistant Professor Department of Computer Science & Engineering Swami Keshvanand Institute of Technology Management & Gramothan Jaipur Rajasthan India Assistant Professor Department of Computer Applications Manipal University Jaipur Rajasthan India Assistant Professor Department of Computer Science & IT Jain (Deemed to be University) Bangalore India

AI Solution for Farmers is an agricultural based project, created to help farmers and to help them in increasing their productivity. Since the technologies are running the world, why agriculture must be deprived of it. Agriculture is one of the most important areas that have major impacts on the economy and society of a country. Technological developments serve as tools to share knowledge and practices of agricultural products and make more satisfactory lives for farmers, traders, policymakers, and the overall society. It is evident that knowledge has become a crucial component in production, society, food security, health, poverty, and other millennium development goals. The use of technology may provide a better approach to solve the problems arising from sowing the seed to harvest the crop. The new technologies like Machine Learning and Data science may be great help to have an eye on the deciding factors to the growth of crop.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real time Machine Learning Approach for a Smart Door Unlocking Using Face recognition System

引用

IOP Conference Series: Materials science and engineering 2021年第1期1130卷

作者： P Rayavel A Sivakumar P V Gopirajan S Surenderanath P Rathnavel Assistant Professor Department of Computer Science and Engineering Sri Sai Ram Institute of Technology Chennai-600044 Tamilnadu India Assistant Professor Department of Information Technology Sri Sairam Engineering College Chennai-600044 Tamilnadu India Assistant Profesor Department of Computer Science and Engineering Saveetha Engineering College Chennai-602105 Tamilnadu India Assistant Professor Department of Electrical and Electronics Engioneering Sri Sai Ram Institute of Technology Chennai-600044 Tamilnadu India

This proposed framework goes about as a home security framework for both Person location and gives security to entryway access control by utilizing facial acknowledgment for the home climate. The more peculiar's face is distinguished inside a home climate accomplished by catching a picture from a web camera and handling will be done on caught pictures. The web camera catches the arrangement of pictures when the individual comes before the entryway. The caught picture is analyzed utilizing our face acknowledgment calculation model. In the event that the individual is the approved one, at that point the entryway is opened. Then again, if the individual isn't the approved one. The picture of the individual is shipped off the power in the event that he perceives the individual and wants to open the entryway. He can distantly get to the entryway and permit the individual in.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Renewable Energy Sources Efficient Detection in Triangulation for Wireless Sensor Networks

引用

IOP Conference Series: Materials science and engineering 2021年第1期1055卷

作者： B Barani Sundaram Nunu Srinivas N Kannaiya Raja Manish Kumar Mishra Dhanabal Thirumoorthy NR Reddy Professor & Associate Dean-ICT Department of Computer Science BuleHora University Bulehora Ethiopia Assistant Professor School of Electrical and Computer Engineering Addis Ababa Institute of Technology Addis Ababa University Addis Ababa Ethiopia Professor Department of Computer Science School of Informatics and Electrical Engineering Ambo University IOT Campus Ambo Ethiopia Department of Computer Science University of Gondar Gondar Ethiopia Lecturer BuleHora University Bulehora Ethiopia Assistant Professor Department of Computer Science Mekelle University Mekelle Ethiopia

It is important for wireless sensor networks (WSNs) to determine whether hubs can be restricted, called localizability recognition. This progression is important for confining hubs, achieving minimal organizations of effort and distinguishing critical in field-based applications. Because of their high calculation and communication costs, centralized graph algorithms are meaningless to an asset-restricted WSN, whereas distributed methodologies can skip a large number of hypothetically locatable hubs in a resource-limited WSN. In this document we are proposing a efficient and successful distributed methodology to solve that address of issue. In addition, we demonstrate our calculation accuracy and analyze the reasons why our calculation will discover increasingly localizable hubs while requiring less established area hubs. The paper introduces a new RSSI-based localization approach triangle as well as centroid placement, utilizing triangle as well as centroid approach to minimize RSSI measurement error. Modelling simulations show that this algorithm can significantly increase the precision of the location compared to the trilateration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Critical Comparative Study of Robot Path Planning in Grid-Based Environment

引用

Journal of Physics: Conference Series 2021年第1期1804卷

作者： R D Dhaniya K M Umamaheswari Research Scholar School of Computing Department of Computer science and Engineering SRM Institute of Science and Technology Kattankulathur-603203 Assistant Professor School of Computing Department of Computer science and Engineering SRM Institute of Science and Technology Kattankulathur-603203

The path planning problem under two-dimensional maps is a fundamental issue in mobile robotics and other applications (unmanned vehicles, and so forth). The traditional algorithms (graph searching, artificial potential field and so forth) are used to find the shortest path that rely on grid-by-grid searching. The main disadvantage of the traditional methods is robot size is not considered and has much redundant in sharp curves which is difficult to guide a robot movement. In this paper, we compared the five baseline approaches of heuristic methods to find the optimal path which reduces the number of turns and time costs to attain a target. The experimental analysis shows that the second-order x derivative has an advantage over other baseline approaches that the search time and the number of turns are reduced.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure IoT via Blockchain

引用

IOP Conference Series: Materials science and engineering 2021年第1期1022卷

作者： Ruchi Garg Poonam Gupta Amandeep Kaur Assistant Professor Electronics and Communication Engineering Department M.M.(Deemed to be University) Mullana Ambala Haryana India Assistant Professor Computer Science and Engineering Department M.M.(Deemed to be University) Mullana Ambala Haryana India Associate Professor Computer Science and Engineering Department M.M. University Sadopur Ambala Haryana. India

Block chain technology had gained popularity because of its use in crypto-currencies like bitcoin. Today uses of blockchain are growing in number of areas like banking, industries, health centers and even security of IOT. Moreover, the use of IOT is growing exponentially every year with its aim in 5G technologies like e- health, smart homes, distributed intelligence etc. but it faces challenges in security and privacy. The privacy of a user data is at a risk because of its (i.e. IoT) centralized client-server model. This centralized approach of the server poses a serious vulnerability to the data security. This data at the server attracts the attackers to enter into the network and invade through the data and schedule attacks or inject a malware. It indicates that the central architecture of IoT possess a compromised confidentiality, integrity, and security of data which disrupts its use as the widespread adoption of this technology. Therefore, it is essential to evade the hostile centralized server architecture for IoT to enhance its security. It implies a need for decentralized architecture to maintain the data. The data can be kept at the different users without any central control with the help of blocks as suggested by Blockchain. This paper addresses the various security issues in IOT and how block chain helps in solving these issues.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Soft Computing Techniques for Clustering in WSN

引用

IOP Conference Series: Materials science and engineering 2021年第1期1022卷

作者： Amandeep Kaur Poonam Gupta Ruchi Garg Associate Professor Computer Science and Engineering Department M.M. University Sadopur Ambala Haryana India Assistant Professor Computer Science and Engineering Department M.M. (Deemed to be) University Mullana Ambala Haryana India Assistant Professor Electronics and Communication Engineering Department M.M. (Deemed to be) University Mullana Ambala Haryana India

The large Wireless Senor Networks (WSNs) comprises Sensor Nodes (SN) in some hundreds with sensing and communication capabilities. Major limitation of WSN is limited energy source of SN. Clustering is one of energy efficient method for energy conservation in WSNs. Clustering is the process to distribute SN in various logical groups known as cluster. Each cluster bears a Cluster Head (CH), who is responsible for transmitting aggregated data of its cluster to Base Station (BS). The literature is enriched by various clustering protocols proposed with the assistance of soft computing. This paper, presents the survey of soft computing paradigm-based clustering protocols.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Consumer product preference prediction towards online shopping

引用

IOP Conference Series: Materials science and engineering 2021年第1期1055卷

作者： S Deepa R Suguna P Sathishkumar C Jamunadevi E N Vidhya Assistant Professor Department of Computer Technology - PG Kongu Engineering College Perundurai Erode India Assistant Professor Department of Computer Science and Engineering Bannariamman Institute of Technology Sathyamangalam India Currently pursuing Master's degree programme in Software Systems Kongu Engineering College Perundurai India

Nowadays E-commerce plays a major role in a business organization. People prefer online shopping rather than offline shopping which helps them to purchase their product from anywhere around the world through mobile phones and laptop. Online shopping websites help people by saving time and product order can be done easily by clicking the product. Online shopping websites are built using the Single Page Application (SPA) framework and the objective of this research is to find the customer preference product prediction by tracking the frequent clicks of the product by the customer. By tracking the clicks of customer we can find their product choice and helps retailer to add the products according to user preference.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Permissioned Blockchain System for Secure Multiparty Computation

引用

Journal of Physics: Conference Series 2021年第1期1998卷

作者： S Garg R Vashisht Software Engineer DLT Labs Hyderabad India Assistant Professor Computer Science and Engineering Department Ajay Kumar Garg Engineering College Ghaziabad India

Permissioned blockchain is the blockchain network that requires access to be part of the network. Participant's actions are governed by the control layer that runs on top of the blockchain. This type of blockchains is preferred by individuals who need role description, identity, and security within the blockchain. Secure multi-party computation (MPC) is a part of cryptography that involves the modeling of procedures for two or more participants who want to work together. These participants involve sharing of input and required computational data for a particular function without sharing their confidential data actively to each other and achieving a common goal which is beneficial to both as the outcome achieved is only revealed to the participants and is highly required for their functional purpose. In this work, SPDZ (Speedz) implementation is explored leveraging additive secret sharing on the private blockchain (Hyperledger fabric). SPDZ protocol is chosen over any other computational protocol as it is highly secured from any active deceptive n-1 participant among the n participants. In this work, a backend is developed that uses a fabric SDK *** library that interacts with the Hyperledger Fabric network. The proposed solution is shown through a demonstration. This paper concludes that for business-to-business scenarios, using SPDZ protocol on permissioned blockchain provides more security against adversaries as permissioned blockchain provides transparency over the participants of the network. As a result, permissioned blockchain is a more secure choice for enterprises to compute confidential data rather than permissionless blockchain.

关键词：

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：