检索结果-内蒙古大学图书馆

Modelling and optimisation of VCR diesel engine parameters fuelled with microalgae methyl-ester: a RSM-coupled Taguchi approach

引用

International Journal of Ambient Energy 2023年第1期44卷 2498-2506页

作者： Ahmad, Aqueel Yadav, Ashok Kumar Singh, Achhaibar Mechanical Engineering Department Netaji Subhas University of Technology New Delhi India Department of Mechanical Engineering Raj Kumar Goel Institute of Technology Ghaziabad India

Due to the high consumption of fossil fuels and their environmental effects, researchers are attempting to develop clean and environmentally sustainable alternative fuels. This study employs a hybrid statistical approach, combining the Taguchi approach and Response Surface Methodology (RSM), to optimise the input parameters of a diesel engine operating on microalgae methyl ester in order to increase engine performance. Through the execution of L16 pre-designed experiments, this work analyzes the significance of three key process parameters: engine load (25-50-75-100%), fuel injection pressure (200-210-220-230 bar), and microalgae biodiesel blends (B20-B40-B50-B100) with respect to brake thermal efficiency (BTE), brake specific fuel consumption (BSFC), carbon dioxide (CO2), and nitrogen oxides (NOx). The response surface methodology was utilised to conduct an experimental investigation. At 71.52% of the engine load, a 204.23 bar injection pressure and a microalgae biodiesel blend of 20% (B20) were found to be the optimal input parameters. The optimum setting of the input parameters provides responses of 31.83% BTE, 278.658 g/kWh of BSFC, 872.053 g/kWh of CO2, and 1725.57 ppm volume of NOx, respectively. The experimental and predicted responses were compared, and it was found that the optimised values were within acceptable limits, with an error of less than 6%. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Microalgae

来源：评论

学校读者我要写书评

暂无评论

Text-to-Image Synthesis using BERT Embeddings and Multi-Stage GAN 1

引用

6th International Conference on Innovative Computing and Communication, ICICC 2023

作者： Rani, Poonam Kumar, Devender Sudhakar, Nupur Prakash, Deepak Shubham Department of Computer Engineering Netaji Subhas University of Technology New Delhi India Department of Information Technology Netaji Subhas University of Technology New Delhi India

ISBN: (数字)9789819930104

ISBN: (纸本)9789819930098

A technique called text-to-image creation is used to create visuals that correspond to provided written descriptions. In this study, we have proposed a Multi-Stage GAN model using BERT Embeddings which consists of three layers of generators and discriminators. Based on a provided text description, the Stage-I GAN creates low-resolution drawings (64 × 64) of a scene’s basic structure and colors. High-resolution pictures (128 × 128) with photorealistic details are produced by the Stage-II GAN using the text description and Stage-I findings as inputs. Further the Stage-III GAN takes Stage-II images as input and adds enticing details and corrects flaws in Stage-II outcomes through refining and also increases the resolution to 256 × 256. For the purpose of creating photorealistic pictures based on text descriptions, the model is evaluated using the Oxford-102 dataset and the CUB dataset and Inception Score as the metric. The IS of Multi-Stage GAN is 3.27 on Oxford-102 dataset and 4.05 on CUB dataset. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Biodiesel production from mahua oil: characterisation, optimisation, and modelling with a hybrid statistical approach

引用

International Journal of Ambient Energy 2023年第1期44卷 2618-2627页

Present study investigates the feasibility of utilising mahua oil as a feedstock for the production of high-quality biodiesel via the transesterification process. Mahua fruit kernels offer an excellent biodiesel source, with an oil content of approximately 35–40%. This study employs a hybrid statistical approach, combining Response Surface Methodology (RSM) and Genetic Algorithm (GA), to optimise the transesterification process. Through the execution of L31 pre-designed experiments, this work analyzes the significance of four key process parameters: methanol-to-oil ratio, catalyst concentration, reaction temperature, and reaction time. The collective influence of these parameters on biodiesel production is comprehensively examined. The GA-derived optimal conditions for biodiesel production are determined as a molar ratio of 7.28 with a 0.93 wt.% catalyst concentration, a reaction temperature of 59.43°C, and a reaction time of 113.62 min. Experimental results validate the model predictions, as the actual yield of Mahua biodiesel reaches 97.54%, with a deviation of only 2.82% from the predicted value. Furthermore, the fuel characteristics of Mahua methyl ester were assessed and compared to ASTM standards. In conclusion, this study highlights the potential of Mahua oil as a valuable and cost-effective feedstock for biodiesel production, thereby opening avenues for its future application as an alternative fuel source. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Biodiesel

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Text Document Using Machine Learning Models for Information Retrieval

Performance Evaluation of Text Document Using Machine Learni...

引用

2023 International Conference on Disruptive Technologies, ICDT 2023

作者： Chowdhury, subhasish Kumar, Suresh Netaji Subhas University of Technology Department of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350323887

Text mining is thought to have a high commercial potential due to the significant amounts of unstructured text data produced on the Internet. The practice of obtaining previously undiscovered, comprehensible, potentially useful patterns or knowledge from a corpus of text data is known as text mining. In this study, we attempt to extract the structured information from the text and then use various machine-learning models to categorize the data. We then look for the model that provides the highest level of classification accuracy. © 2023 IEEE.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Intelligent personalised learning system based on emotions in e-learning

引用

Personal and Ubiquitous Computing 2023年第6期27卷 2211-2223页

作者： Karthika, R. Jesi, V. Elizabeth Christo, Mary Subaja Deborah, L. Jegatha Sivaraman, Audithan Kumar, Sanjeev Department of Computer Science and Engineering University College of Engineering Tindivanam Tamil Nadu Melpakkam604001 India Department of Networking and Communications School of Computing College of Engineering SRM Institute of Science and Technology Chennai Kattankulathur603203 India Department of Information Technology Netaji Subhas University of Technology New Delhi110078 India Department of Electronics and Communication Engineering Netaji Subhas University of Technology New Delhi110078 India

One of the greatest challenges in the success of a personalised e-learning system lies in the behaviour identification of the learners during the learning and evaluation phase. The content delivery in an e-learning system must be modified and updated periodically according to the preference and behaviour of the learners. Usually, the behaviour of the learners drastically changes according to their affective states during the learning phase. The accurate identification of the learner’s negative emotions and addressing such emotions carefully in a positive sense can greatly provide success to the learners. In this paper, the learner’s emotions especially frustration emotion are automatically and accurately estimated using the information received from learning management systems (LMS) using the Takagi sugeno fuzzy inference engine. Based on this estimation, several motivational messages are distributed according to the identified emotions which had greatly helped them to succeed during e-learning. The motivational messages that are used for sending to the learners are based on regulatory fit theory. Several kinds of statistical tests are used in this paper for deep analysis. Two sets of learners, namely, control and experimental sets, are identified from undergraduate students. Experimental results are shown for these two sets to reveal the increase in their emotional strength after receiving the motivational messages. Statistical analysis t-test is also applied to the two sets, and the experimental results have shown that there is a significant difference between the two groups which shows the dominance of the proposed system. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Legal Case Classification Using Machine Learning with NLP

Legal Case Classification Using Machine Learning with NLP

引用

2023 International Conference on Data Science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Tomar, Manjusha Singh Gupta, Vishal Netaji Subhas University of Technology Department of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350348910

In India, offences occur daily;crime can be minor or severe. The Indian jurisdiction system provides justice in every severity of the case. However, reporting a crime to get justice requires proper steps. Cases involving murder fall under criminal cases, while cases related to a family dispute over a property fall under civil cases. Accurately dividing legal circumstances into civil and criminal categories is essential for efficient legal case management and decision-making processes. In recent years, deep learning models have advanced significantly in problems in evolving natural language processing. This study offers a strategy based on BERT for classifying legal cases as civil or criminal. The recommended model fine-tunes the early halting and modifies the BERT-Base model using a hyperparameter on a corpus of labelled court case documents, using BERT's ability to gather contextual information and precise relationships between words and sentences. The attention mechanism in BERT enables the model to understand the nuances of the legal dataset and distinguish between civil and criminal scenarios based on the given legal context. Experimental results on a large dataset of legal cases show our method's effectiveness and excellent accuracy, precision, recall, and F1score in categorizing legal cases. The BERT-based model exhibits promising potential for automating case categorization, enabling efficient case management, assisting legal professionals in decision-making processes, and assisting regular people in making informed decisions by providing insightful analyses and predictions based on the available data, with an accuracy of 92.9 and an F1 score of 0.93. © 2023 IEEE.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

PCA-Based Feature Selection and Hybrid Classification Model for Speech Emotion Recognition 6th

PCA-Based Feature Selection and Hybrid Classification Model ...

引用

6th International Conference on Innovative Computing and Communication, ICICC 2023

作者： Tripathi, Astha Rani, Poonam Department of Computer Engineering Netaji Subhas University of Technology New Delhi India

ISBN: (纸本)9789819933143

By eliminating repetitive and irrelevant features, feature selection algorithms try to minimize the number of features. Principal component analysis (PCA) is introduced as a feature selection approach in this paper, while a hybrid model of SVM with random forest (RF) is applied as a classifier. Furthermore, this study has highlighted the comparison of outcomes obtained with and without the use of the feature selection technique. This work utilizes the RAVDESS, EMOVO Corpus, and SUBESCO database and takes into account the classification accuracy performance metric when evaluating the proposed SER system. The experimental outcomes show that the suggested method offers extremely successful and reliable emotional categorization performance as 88% for SUBESCO dataset, 80% for EMOVO dataset, and 74% for RAVDESS dataset. It has been demonstrated that the suggested approach can successfully reduce emotional confusion and improve the emotion recognition percentage for multilingual dataset. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Stock Price Prediction Using Time Embedding and Attention Mechanism in Transformers

Stock Price Prediction Using Time Embedding and Attention Me...

引用

2023 International Conference on Data Science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Das, Sourav Nagpal, Bharti Netaji Subhas University of Technology Department of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350348910

Predicting stock prices accurately is a complex task that involves analyzing a wide range of factors such as company performance, industry trends, market conditions, and even global events. Recently, transformer-based models have shown promising results for sequential data analysis, including stock price prediction. However, predicting stock prices accurately requires considering the temporal patterns in the data, which can be achieved by incorporating time embedding techniques into the model. Here in this paper a transformer-based model was proposed for stock price prediction that incorporates time embedding and the moving average technique. The proposed model uses historical stock prices and financial indicators as input, and the output is the predicted stock prices. Time embedding is used to capture the temporal patterns in the stock prices, and the moving average technique is used to remove the noise in the input data and improve the models accuracy. The performance of proposed model which is based on transformer is evaluated on publicly available dataset of various companies i.e IBM, APPLE and TATAMOTORS. The results we achieved is really good and transformer-based models have really proven to be suited for Stock price prediction. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Aqua Clear: Efficient Water Management for home water supply 2023

Aqua Clear: Efficient Water Management for home water supply

引用

15th International Conference on Contemporary Computing, IC3 2023

作者： Rastogi, Shrey Sharma, Shivam Kumar, Suraj Singal, Gaurav Department of Computer Science and Engineering Netaji Subhas University of Technology Delhi India

ISBN: (纸本)9798400700224

The quality of water resources available across the world have been degrading much faster than ever before. Therefore, judicious use of water resources has become an important topic as these resources get evermore scarce. Moreover, efficient treatment and utilization of these resources domestically is another factor to be considered. Our proposed IoT-based system aims to enhance the water utilization in households as in preventing excess use of Reverse Osmosis (RO) and prevent highly contaminated water from entering the house water-storage. The system uses sensors which measure physical characteristics of water - its temperature and Total Dissolved Solids (TDS) which is gathered by the microcontroller and displayed to the user on a smartphone. Based on the value of TDS of water, the system automatically controls the water filter system by directing unfiltered water to the suitable filter (RO or Non-RO) as well as controlling the water-storage tank system. © 2023 ACM.

关键词： Water filtration

来源：评论

学校读者我要写书评

暂无评论

Implementing Blockchain technology in Healthcare: An Overview, Key Requirements, and Challenges 12th

Implementing Blockchain Technology in Healthcare: An Overvie...

引用

12th International Conference on Soft Computing for Problem Solving, SocProS 2023

作者： Raj, Aman Verma, Reshu Kataoka, Kotaro Department of Computer Science and Engineering Patna India Netaji Subhas University of Technology New Delhi India Indian Institute of Technology Hyderabad India

ISBN: (纸本)9789819731794

This research aims to develop a theoretical design for a healthcare app that utilizes blockchain technology to manage patient and physician databases. The study identifies gaps in earlier models that primarily focused on the use of blockchain in the finance and economic sectors. The ultimate goal is to create a smartphone app that will enable surgeons to manage their patients more efficiently and help patients compare costs, procedures, and pre/post-surgery preparations using Bitcoin as payment. The research involves an analysis of the present literature on blockchain technology in healthcare and space missions and uses a conceptual framework to develop the theoretical design. The results of the study include the development of a theoretical design for the healthcare app that could increase efficiency in patient management, cost savings, and simplify the payment process. The study hopes to encourage medical stakeholders to participate in the blockchain network, which could lead to increased network sustainability and security. Overall, the research highlights the potential benefits of blockchain technology in healthcare, particularly in managing patient and physician databases, and proposes a design that could lead to increased efficiency and cost savings. The study aims to contribute to the existing conceptual framework for medical stakeholders and encourage their participation in the blockchain network. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Blockchain

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：