检索结果-内蒙古大学图书馆

Comparative analysis of regression models to predict the performance of the dual fuel engine operating on diesel and hydrogen gas

引用

International Journal of Hydrogen Energy 2025年 141卷 585-597页

作者： S, Priya Feenita, C. Goel, Uday T, Manoranjitham Duraisamy, Boopathi Subramanian, Balaji Ganeshan, Kavitha Josephin JS, Femilda Albeshr, Mohammed F. Pugazhendhi, Arivalagan Varuvel, Edwin Geo Department of Computing Technologies College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur603 203 India Department of Automobile Engineering College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur603 203 India Department of Mechanical Engineering College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur603 203 India Department of Science and Humanities Agni College of Technology Thazhambur Chennai600130 India Department of Computer Engineering Faculty of Engineering and Natural Sciences Istinye University Istanbul Turkey Department of Zoology College of Sciences King Saud University P.O. Box. 2455 Riyadh11451 Saudi Arabia Research and Development Office Asia University Taichung City Taiwan Department of Mechanical Engineering Faculty of Engineering and Natural Sciences Istinye University Istanbul Turkey Department of Autoronics Institute of Automobile Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai602105 India

Internal combustion engines (ICEs) have long been essential in both the transportation and industrial sectors, providing primary power for vehicles, ships, and machines globally. Optimising the efficiency of ICEs is vital for decreasing their environmental impart, as increased fuel efficiency and lower emissions play a significant role in mitigating the effects of climate change as well as improving air quality. This study employed 15 regression algorithms and machine learning approaches to analyse and anticipate the performance parameters of ICEs that run on hydrogen-diesel in dual fuel mode. The input parameters include engine torque, speed, hydrogen flow rate, brake power and diesel energy share to hydrogen supply and the output parameters are brake specific fuel consumption, brake thermal efficiency, volumetric efficiency and actual air intake. The model's performance is evaluated using five different performance metrics. Among the studied algorithms, the RANSAC Regressor demonstrated exceptional predictive capability, reaching an R-squared value of 0.999, a mean squared error (MSE) of 0.0064, a root mean square error (RMSE) of 0.08, and a mean absolute error (MAE) of 0.057. These outcomes show the algorithm's accuracy and precision in capturing the complicated data of engine system. The equivalency ratio, volumetric efficiency, brake thermal efficiency, brake specific fuel consumption, and actual air intake are among the critical performance outputs that are optimised by utilizing key input parameters like engine load, rotational speed, hydrogen flow rate, brake power, and the diesel fuel energy share. This study highlights the significant potential of machine learning in optimising ICE performance, offering a reliable alternative to traditional experimental analysis by reducing both risk and economic costs. The research findings also support the paradigm shift towards intelligent and sustainable energy systems by compellingly advocating for the inclusion of da

关键词： Air intakes

来源：评论

学校读者我要写书评

暂无评论

Unaligned Federated Knowledge Graph Embedding 23rd

Unaligned Federated Knowledge Graph Embedding

引用

23rd International Semantic Web Conference, ISWC 2024

作者： Chen, Deyu Zhu, Hong Gu, Jinguang Chen, Rusi Xie, Meiyi School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China State Grid Hubei Electric Power Research Institute Wuhan China

ISBN: (纸本)9783031778438

Recently, knowledge graph embedding (KGE) methods under the federated learning paradigm have received much attention. Its privacy-preserving decentralized training method effectively utilizes the knowledge graphs held by different clients. Existing federated KGE frameworks collaboratively train the global model by aggregating aligned entity embeddings among clients. However, in real-world scenarios, the lack of aligned entities and the high heterogeneity among knowledge graphs constrain their potential. To address these issues, we propose a federated KGE framework that does not depend on any aligned set but uses structure information. The framework introduces a set of basis edges to model the general structure information. Then, we use two separate modules on clients to encode structure and feature representations, respectively. Finally, clients only upload structure parameters for aggregation on the server. The framework uses a new unaligned federated KGE paradigm to tackle the heterogeneity of multi-source knowledge graphs. Experimental results on benchmark datasets show that UniFE achieves superior results even compared to federated KGE frameworks using the aligned set. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Advanced Machine Learning Techniques for Predicting Health Status in Smoke-Exposed Environments 2

Advanced Machine Learning Techniques for Predicting Health S...

引用

2nd International Conference on Automation, Computing and Renewable Systems, ICACRS 2023

作者： Duraisamy, Premkumar Nitheshvaran, B. Kumar, Nalin S. Irshad, B. Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India

ISBN: (纸本)9798350340235

S moker health status is a vital focus in public health and medical research due to smoking's impact on preventable diseases and premature death worldwide. Recognizing the diverse effects of smoking on health is crucial, spanning both immediate and long-term consequences across multiple physiological systems. This research underscores the pressing importance of comprehending smoking's far-reaching impacts on health and emphasizes the necessity of effective interventions and cessation strategies to mitigate i ts adverse effects. This study aims to utilize diverse machine learning algorithms to predict the health status of smokers accurately. The primary objective is to equip healthcare professionals with a reliable diagnostic tool for early and precise identifi cation of smoking-related health risks, ultimately saving lives. Leveraging a comprehensive dataset, various algorithms, such as Boost, LightGBM, CatBoost, Random Forest, AdaBoost, and others, are explored. Through rigorous experimentation, the Boost algorithm stands out, achieving an impressive 96.2% accuracy in predicting the health status of smokers. © 2023 IEEE.

关键词： Classification Kaggle dataset Machine learning Smoker health status Voting ensemble method

来源：评论

学校读者我要写书评

暂无评论

Predicting Land Cover Changes with Convolutional LSTM Networks: A Case Study of Chatham, Massachusetts

Predicting Land Cover Changes with Convolutional LSTM Networ...

引用

2024 IEEE International Conference on Modeling, Simulation and Intelligent Computing, MoSICom 2024

作者： Kavitha, J.C. Subitha, D. Bhandari, Divyansh Jaluka, Devesh Kumar Vellore Institute of Technology School of Computer Science and Engineering Chennai600127 India Vellore Institute of Technology School of Electronics and Engineering Chennai600127 India

ISBN: (纸本)9798331533311

Land use and land cover changes has become crucial for natural resource management and monitoring, particularly in urban planning. Remote sensing and geographical information systems analyze the changes in land use and land cover, promoting sustainability. Remote sensing images are the major data sources for land cover classification. High spatial resolution images enable more precise analysis and identification of land cover data types. However, better spatial resolution creates new challenges to the existing classification and prediction methods. This research work outlines a new model that integrates the Convolutional Neural Networks and Long Short-Term Memory network model for the prediction of dynamic changes in land cover patterns from historic satellite images. The proposed model is constructed for Chatham, Massachusetts, prediction from Google Earth timelapse imagery taken over 39 years to compile a sequence of 39 annual satellite images. The images are preprocessed to 256 × 256 pixels and image normalization ensured efficient data handling. The proposed model predicted land cover over the next three years and demonstrated the model's capacity to capture both geographical and temporal patterns in the data. Evaluation of metrics, such as the training and validation loss, showed good performance by the model. Despite some limitations in image resolution and iterative prediction, the findings show that CNN-LSTM models could be very useful for land cover forecasting, providing important guidelines for future study and practical applications in the context of environmental management. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid AI-Driven Techniques for Enhancing ZeroDay Exploit Detection in Intrusion Detection System (IDS) 3

Hybrid AI-Driven Techniques for Enhancing ZeroDay Exploit De...

引用

3rd International Conference on Artificial Intelligence, Internet of Things and Cloud Computing technology, AIoTC 2024

作者： Tariq, Ahmed Hasham Ibn E Tariq, Moazan Basoud Ibn E Lu, Songfeng School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518063 China

ISBN: (纸本)9798331530280

Zero-day exploits present significant risks to cybersecurity by exploiting unknown vulnerabilities, making their identification and mitigation a key problem. Conventional Intrusion Detection Systems (IDS) frequently depend on signature-based or anomaly-based methodologies, which are ineffective in identifying new and sophisticated incidents of assault. This paper provides a new hybrid AI-driven strategy to boost zeroday exploit detection by the combination of deep learning and ensemble learning approaches. We have taken the UNSW-NB15 dataset, a complete and diversified reference for network intrusion models, to train and analyze our model. The suggested system leverages a hybrid architecture integrating Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to capture both spatial and sequential features of network traffic efficiently. To further increase detection accuracy and resilience, we add ensemble approaches by combining random forest, gradient boosting, and Support Vector Machine (SVM) classifiers through a weighted voting mechanism. Our ensemble model achieves a detection accuracy of 97.8%, outperforming standard anomaly-based (IDS), vision transformer (ViT) and bidirectional encoder representations from transformers (BERT) by a wide margin. The model also demonstrates a low false-positive rate of 0.022 and high detection rates across multiple types of attacks, including previously undiscovered zero-day flaws. Performance studies employing criteria like accuracy, recall, F1score, AUC-ROC, false-positive rate, and detection rate indicate the importance and reliability of our methodology. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Pesticide Usage Forecasting for Agriculture using Prophet Model 5

Pesticide Usage Forecasting for Agriculture using Prophet Mo...

引用

5th IEEE International Conference for Emerging technology, INCET 2024

作者： Wani, Afshan Hassan Moharana, Bhimasen Samant, Tapaswini De, Utpal Chandra Dey, Snehasis Banerjee, Shobhan Department of Computer Science and Engineering Lovely Professional University Punjab India School of Electronics Engineering Kalinga Institute of Industrial Technology Bhubaneswar India School of Computer Applications Kalinga Institute of Industrial Technology Bhubaneswar India College of Engineering Bhubaneswar India Department of Engineering Technology Birla Institute of Technology and Science Pilani India

ISBN: (纸本)9798350361155

Agriculture plays a vital role in our day-to-day life for the life sustenance of not just human beings but also various domestic and livestock animals. In addition to this, agriculture also contributes significantly to the economy of a country, impacting its growth across the globe. India had always been an agriculture-dominated country before the companies from the West started investing in India. But alongside agriculture come various challenges such as infestation by insects or weeds which eventually lead to the damage of crops and even diseases. But pesticides can even contribute to the contamination of soil, water, and other vegetation in areas where they are been used. In this paper, we have used the Prophet model to study the use of pesticides and analyze the trends of usage of organic pesticides over inorganic pesticides. © 2024 IEEE.

关键词： Pesticides

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Techniques and Methodology Available for Lung Cancer Detection

Artificial Intelligence Techniques and Methodology Available...

引用

2023 International Conference on Sustainable Computing and Smart Systems, ICSCSS 2023

作者： Kanaga Priya, P. Sivakumar, T. Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350333602

Cancer is a term used to describe the body's aberrant cells growing out of control, which can occur in various body parts. With over a hundred types of cancer known to exist, delays in treatment can lead to severe health issues and, in some cases, loss of life. This study reviews the current methods used to detect lung cancer through image processing. The study suggests that artificial intelligence (AI) is effective in processing large datasets, providing accurate and efficient results for cancer detection. However, implementing these systems on a large scale presents several challenges, such as the capture of images, preparation of images, segmentation, and information management. Classification strategies must also be developed to ensure compatibility with AI. This study examines various imaging techniques and methodologies available for detecting cancer using a computer-aided user interface, which is essential to improve healthcare and meet the growing patient population's needs. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Ball milled Mg/Al hydroxides modified nitrogen-rich biochar for arsenic removal: performance and governing mechanism

引用

Carbon research 2023年第1期2卷 1-14页

作者： Wang, Ming Yan, Jinlong Diao, Yusen Zhou, Xiangqian Luo, Ting Wang, Hui Quan, Guixiang Sun, Xinyu Wang, Jun School of Environmental Science and Engineering Yancheng Institute of Technology Yancheng224051 China Jiangsu Engineering Research Center of Biomass Waste Pyrolytic Carbonization & Application Yancheng224051 China Industrial Technology Research Institute Yancheng Institute of Technology Yancheng224051 China

Layered double hydroxides (LDHs) are widely used as effective adsorbents for wastewater treatment due to their simple synthesis, controllable structure, strong stability, large surface area, and large interfacial spacing. In this study, modified-biochar (BMBC) and Mg/Al modified-biochar composite (Mg/Al-BC) were directly prepared using ball milling technology to effectively adsorb As(V), and nitrogen-rich biochar was obtained through pyrolysis using shrimp shells as precursors. Compared to pristine biochar, the oxygen-containing functional groups of Mg/Al-BC increased by 71.9%, and the particle average diameter decreased from 14.26 nm to 12.56 nm. The kinetics and isothermal models of arsenic adsorption were examined in batch experiments to investigate the impacts of pH, temperature, and co-existing anions. The adsorption capacities for As(V) followed the order: Mg/Al-BC > BMBC > BC, with their respective maximum adsorption capacities measured at 22.65, 6.73, and 0.48 mg/g. The arsenic adsorbed onto Mg/Al-BC was dependent on pH and coexisting anions. Precipitation, ion exchange, surface complexation, and electrostatic interaction were the possible governing adsorption mechanisms. Protonation of pyridinic-N/quinone groups in biochar contributed to the electrostatic attraction between arsenic anion and quaternary ammonium cation. Stable reusability indicates that the ball milled Mg/Al-BC composite could be a promising adsorbent for arsenate removal from polluted water. Graphical Abstract: [Figure not available: see fulltext.] © 2023, institute of Eco-environmental and Soil sciences, Guangdong Academy of sciences.

关键词： Wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

NLP based Analysis and Detection of Unethical Text 2

NLP based Analysis and Detection of Unethical Text

引用

2nd International Conference on Sustainable Computing and Data Communication Systems, ICSCDS 2023

作者： Khandekar, Apurva Hema, Chekuri Devi Meghana, Alle Mounika, Akuraju Vaishnavi, V.S. Computer Science and Engineering Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad India

ISBN: (纸本)9781665491990

In the present scenario, the internet has enabled everyone to express their opinion. As every coin has two sides, it paved a way for increased negativity and intolerance. In this context, unethical text includes offensive comments and hate speech targeting a group or an individual based on their characteristics such as race, religion or gender and that may threaten social peace. So, the unethical text should be eliminated before it reaches a user where identifying an immoral text plays a pivotal role. Various methods are used in identifying a text, one such method, widely known as Natural Language Processing (NLP) is used to perform text analysis in the process of detecting the unethical text. NLP enables us to perform tokenization, embedding matrix, padding and identification of semantic relationships, which helps to analyse the text data efficiently. Different algorithms were used to detect the unethical text, this study has used ISTM and Bi-LS TM to identify whether the user's statement is offensive or not. The better and accurate model is considered and a web page is built on it. It predicts the offensiveness of text present in user input. In this way, the proposed model detects the unethical text on the web, which can be used to eliminate unfiltered comments. The best model is achieved by using the Bi-ISTM with an accuracy of 86.4%. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Early Prediction of Alzheimer’s Disease Using Ensemble Learning Models

Early Prediction of Alzheimer’s Disease Using Ensemble Lear...

引用

International Conference on Machine Learning and Big Data Analytics, ICMLBDA 2022

作者： Singh, Divjot Mishra, Ashutosh Computer Science and Engineering Department Thapar Institute of Engineering and Technology Patiala India

ISBN: (纸本)9783031151743

The human brain is the most complex part as it controls numerous operations of the human body. For the past few decades, works have been going on to study the working of brain and how to make models that can replicate its working. Artificial intelligence is one such advanced field that trains on data we collect and predicts the output like a human brain. On the other hand, there are many diseases related to brain that have been discovered over time. These diseases progress with the passage of time, and, due to their slow rate of progression, it becomes difficult to detect them at early stage. Alzheimer’s disease (AD) is one of the neurodegenerative diseases which damages the brain permanently and becomes untreatable at the higher stages. Thus, it becomes very important to detect AD at an early stage to increase the life span of the person detected. The main predicament is to detect AD at an early stage and the selection of features responsible for it. The objective of this study is to predict AD at an early stage and to identify the features that facilitate its early prediction using ensemble learning. The proposed multiple ensemble method uses the selected features to achieve an accuracy of 82.40% and with higher ROC. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Brain

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：