检索结果-内蒙古大学图书馆

Organ Risk Prediction Using Deep Learning and Neural Networks 1

3rd International Conference on Sustainable Advanced Computing, ICSAC 2021

作者： Bafna, Simran Shankar, Achyut Nehra, Vanshika Thakur, Sanjeev Mala, Shuchi Department of Computer Science Amity School of Engineering and Technology Amity University Noida India

ISBN: (数字)9789811690129

ISBN: (纸本)9789811690112

Parkinson’s disease is a chronic degenerative condition caused predominantly by a deficiency of dopamine in the brain. Due to a long latency before the first dopamine damage, PD is mostly not diagnosed at its early stage. The precise and successful diagnosis have been, therefore, a major challenge. To resolve the precise diagnosis of the problem of the disease, we proposed a non-invasive prediction method based on convolutional neural network prognostic modelling for specific and effective Parkinson’s disease diagnosis by diagnosing the organs at risk at different stages and also its severity. Deep learning-based approaches have recently shown promise for the tasks of medical image processing and disease detection. The proposed deep learning-based approach first extracted features from the clinical data and then merged them to predict organs at risk at various stages. Our findings show that the addition of imaging data to non-imaging clinical data in patients with PD is helpful in predicting outcomes. The suggested approach that combines clinical evidence from both imaging and non-imaging shows great promise for outcome prediction in patients with PD. This paper provides a systematic analysis of the prediction of Parkinson’s disease with an accuracy rate of overall 90.93%. This paper also presents the review of findings obtained in the literature by numerous studies to predict Parkinson’s diseases. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Fingerprint-Based Multifactor Authentication For Bank Transaction 18

Fingerprint-Based Multifactor Authentication For Bank Transa...

引用

18th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2024

作者： Kaur, Mananjeet Kaistha, Shreya Aggarwal, Shubhani Budhiraja, Ishan Chaudhary, Rajat Bindle, Abhay Amity University Department of Computer Science Engineering Punjab India Bennett University School of Computer Science Engineering and Technology Uttar Pradesh Greater Noida India Maharishi Markandeshwar University Department of Electronics and Communication Engineering Haryana Mullana Ambala India

ISBN: (纸本)9798350391725

Robberies of ATMs have been on the rise in the last few years and are becoming a major concern for Banks and their customers. Currently, we operate ATMs using a PIN that can become a victim of theft, guessed, and can be hacked while the transaction is going on. This raises a question on the security of ATM transactions and requires new techniques and schemes that can offer a second level of protection. Considering these security concerns, we proposed a security check on the existing ATM systems. We authors have created two applications that present the new technique. Our banking application, called Fingerpay, works like traditional banking applications with an added feature where the user can enable the MFA (Multi-factor Authentication) through MPIN verification. In this case, a request for fingerprint authentication is prompted as a notification on the user's registered mobile number. Upon successful authentication, the transaction is authorized and completed securely. The key contribution of this research lies in the formation of a secure and user-friendly MFA system for ATM transactions. By integrating fingerprint authentication with existing banking applications, users are prompted to verify their identity through a registered fingerprint scan during ATM transactions. This additional layer of authentication increases security by significantly reducing the risk of unauthorized access and fraudulent transactions. In addition, biometric authentication outperforms traditional methods, including increased accuracy, reliability, and resistance to identity theft or impersonation. In the end, this proposal will go a long way in resolving the problem of ATM transactions. Further, this report contains the introduction, design and implementation part of the proposed model. © 2024 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Implementation of Intrusion Detection System Using Various Machine Learning Approaches with Ensemble learning

Implementation of Intrusion Detection System Using Various M...

引用

2023 International Conference on Advancement in Computation and computer Technologies, InCACCT 2023

作者： Pandit, Pragati Vijaykumar Bhushan, Shashi Waje, Pratibha Vitthal Shri Jagdishprasad Jhabarmal Tibrewala University Computer Science and Engineering Jhunjhunu India Amity University Amity School of Engineering and Technology Department of Computer Science Punjab Mohali India Sir Visvesvaraya Institute of Technology Information Technology Chincholi Nashik India

ISBN: (纸本)9798350396485

recent years have seen an increase in advanced threat attacks, yet feature filtering-based network intrusion detection systems have a number of shortcomings that make it challenging for security managers and analysts to identify and thwart network intrusions in their organizations. Information systems are routinely protected and damage is minimized using techniques for detecting intrusions. It protects against dangers and weaknesses in real-world and virtual computer networks. Effective intrusion detection systems are now typically created using machine learning techniques. Neural networks, statistical models, rule learning, and ensemble techniques are examples of machine learning techniques for intrusion detection. Machine learning ensemble techniques are renowned for their superior performance during the learning process. For the creation of a successful intrusion detection system, a suitable ensemble technique must be investigated. In this paper, we introduced a novel ensemble method for intrusion detection in the network along with a combination of decision tree, random forest, extra tree, and XGBoost algorithms. The suggested method was created utilizing the Python programming language and aids in improving detection accuracy. Utilizing the CICIDS2017 dataset, the constructed system is evaluated based on numerous evaluation criteria, including precision, recall, and fl-score. The ensemble approach significantly raises the detection accuracy. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Improved Air Pollution Prediction: A Combined LSTM-SVR Approach 4

Federated Learning for Improved Air Pollution Prediction: A ...

引用

4th IEEE Annual Flagship India Council International Subsections Conference, INDISCON 2023

作者： Abimannan, Satheesh John, A. Shukla, Saurabh Satheesh, Dhivyadharsini Amity University Maharashtra Department of Computer Science and Engineering Mumbai India Galgotias University Department of Computer Science and Engineering UP Greater Noida India School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350333558

In this research paper, we introduce a unique approach to predict air pollutant concentrations. The method involves combining two pre-existing models, LSTM and SVR, by utilizing federated learning. Our proposed model is evaluated based on air quality data gathered by the Taiwan Environmental Protection Agency (EPA). By using federated learning, we can create a global model that taps into the collective knowledge of all 70 data centers while safeguarding data privacy and security. This novel method has significant implications for addressing joint air pollution mitigation and environmental protection. Additionally, the research paper presents performance comparisons of various models across three locations in Taiwan. We demonstrate the efficiency of our FL-ALSTM and FL-SVR models in predicting air pollutant concentrations. Our findings show that the FL-ALSTM model outperforms other models, improving predictions of air pollution levels by more than 95%. Overall, our study underscores the potential of federated learning in advancing air pollution prediction and environmental sustain ability. © 2023 IEEE.

关键词： Environmental Protection Agency

来源：评论

学校读者我要写书评

暂无评论

A Novel Cryptographic Encryption Technique for the Security Enhancement of Electronic Transactions 14

A Novel Cryptographic Encryption Technique for the Security ...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Boussi, Grace Odette Gupta, Himanshu Hossain, Syed Akhter Fila Rudy, J.J. Amity University Amity Institute of Information Technology Noida India University of Liberal Arts Computer Science and Engineering Department Bangladesh Sharda University School of Engineering and Technology Greater Noida India

ISBN: (纸本)9798350335095

Cybersecurity has been a trending topic for years now, different propositions, studies, and work have been suggested in various forms by other authors all over the world, but the impact of crime is still around us. In the present area, we cannot say that data is safe when it is hidden from an unauthorized person, but it is safe when the intruder cannot understand it, hence encryption is the suitable solution at the moment. Encryption is one of the techniques that we use to protect our data from unauthorized persons. In this technique, we do not stop the unauthorized person from accessing our information, but we made our data appear in an incomprehensive form to the intruder, only the person with the correct key can decrypt the encrypted message. Many encryption techniques are available, and the commonly used and modern ones are RSA, AES, and HAS, each of them is suitable for different scenarios and are all helpful for cyber security. In this paper, we will propose a framework that provides an additional layer of security for any sensitive information in general and those in the banking sector. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Assessment and Summary of Inverter and Induction Motor Efficiency in Dual Electric Vehicle Drive Systems Across Urban and Highway Driving Conditions 7

Assessment and Summary of Inverter and Induction Motor Effic...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Manjunatha Naresh, B. Dutt, Amit Chaturvedi, Prateek Balaram, A. Bargavi, Y. Krishna New Horizon College of Engineering Department of Mechanical Engineering Karnataka Bangalore India Institute of Aeronautical Engineering Telangana Hyderabad India Lovely Professional University Punjab Phagwara India Amity University Amity School of Engineering & Technology Uttar Pradesh Greater Noida India Mlr Institute of Technology Department of Computer Science & Engineering Telangana Hyderabad India Griet Department of Computer Science & Engineering Bachupally Hyderabad India

ISBN: (纸本)9798350350067

Recent studies have shown that battery-powered motors and power electronic inverters are crucial parts of contemporary dual electric vehicle driving systems. Consequently, the traction engine and its accompanying drive must run at peak efficiency all the way through the driving schedule. The traction motor and drive system in a hybrid electric vehicle (HEV) typically utilize the full range of torque and speed operating conditions. With this in mind, the objective of this work is to estimate the efficiencies of the inverter and motor over common urban and highway driving patterns. The significant losses within a standard three-phase DC/AC traction inverter, including switching and conduction losses in the insulated-gate bipolar transistors and antiparallel diodes, are modelled and approximated for both urban and highway driving. Using an Automobile Simulator program, a medium-sized SUV equipped with an induction motor was simulated, accounting for copper losses in the stator, rotor, and core. The average efficiencies of the inverter drive and induction traction motor are then evaluated and summarized for both urban and highway driving conditions. Finally, the overall efficiency of the traction motor drive system is assessed based on the individual component performance analyses. © 2024 IEEE.

关键词： Traction motors

来源：评论

学校读者我要写书评

暂无评论

Predicting Purchases and Personalizing the Customer Journey with Artificial Intelligence 11

Predicting Purchases and Personalizing the Customer Journey ...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Malik, Varun Mittal, Ruchi Chaudhry, Rishi Yadav, Suman Avdhesh Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Institute of Management Studies and Research Maharshi Dayanand University Haryana Rohtak India Amity School of Engineering and Technology Amity University Department of Computer Science and Engineering Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350350357

A mastery of consumer behaviour analysis and the ability to personalise the customer experience are prerequisites for success in today's cutthroat business climate. In order to improve the customer experience and make purchase predictions, this research explores the world of artificial intelligence. Using a systematic three-step technique, this study aims to improve consumer purchase prediction and provide individualised customer experience. The dataset is preprocessed using Enhanced Z-score normalisation first. This will ensure uniformity and mitigate the impact of extreme cases. After a better collection of features is found using Recursive Feature Elimination (RFE), the dataset is optimised for classification tasks. Lastly, state-of-the-art technology is used in the research via the usage of Enhanced Long Short-Term Memory (LSTM) networks for classification and prediction. Better LSTM networks may be able to detect nuanced changes in customer behaviour, resulting in more accurate predictions. Our study aims to contribute to the advancement of AI applications in CRM by following this rigorous process. We want to help companies better their strategy, offer more personalised experiences, and boost the possibility of consumers completing a purchase by delivering relevant insights. © 2024 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

Classification of Common Insects Using Transfer Learning and ResNet50 9

Classification of Common Insects Using Transfer Learning and...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Sakshi Sharma, Chetan Kishore, Jaydeep Bhardwaj, Vivek Amity Institute of Information Technology Amity University Noida India UpGrad Education Private Limited Bangalore India School of Computer Science and Engineering Manipal University Jaipur Jaipur India

ISBN: (纸本)9798350377972

The escalation of the global temperature and the pressure on the fields is at an all-time high. To feed the rising population, insecticides, and pesticides are likewise at an all-time high. With the growing temperature due to global warming and the increasing employment of pesticides to feed the people, one class of creatures suffers the direct hit: insects. On the other hand, the growing warmth leaves them vulnerable to death due to bad environmental circumstances. On the other hand, the increasing employment of pesticides extirpates innocuous insects with hazardous insects. There is a continual requirement to monitor the growth and condition of such insects to maintain the sustainability of the environmental system. However, accomplishing such a big work manually is not only impossible but fruitless, too, since few insects of various classes provide identical looks. To cope with such challenges related to this work, a transfer learning-based ResNet50 network is presented to automatically detect, categorize, and consequently track the insect populations to take future measures. The model obtains a recognition accuracy of 91.45%. © 2024 IEEE.

关键词： Invertebrates

来源：评论

学校读者我要写书评

暂无评论

Fake News Detection using Machine Learning

Fake News Detection using Machine Learning

引用

2022 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing, COM-IT-CON 2022

作者： Gupta, Varun Mathur, Rohan Sahai Bansal, Tushar Goyal, Anjali Amity University Amity School of Engineering and Technology Department of Computer and Science and Engineering Uttar Pradesh Noida India Sharda University School of Engineering and Technology Department of Computer and Science and Engineering Uttar Pradesh India

ISBN: (数字)9781665496025

ISBN: (纸本)9781665496025

With the advent of the World Wide Web and the swift advocacy of online platforms paved the way for news propagation that has never been seen in the past. With the present situation of social media platforms, users are developing and sharing more information when compared to the last five years, some of them are not even related to real life. Classifying the text automatically is a tedious and tough job to do. To give a verdict on the truthfulness of an article, a professional too needs to explore multiple aspects of the domain first. Machine learning algorithms are popularly being used to detect the truthfulness of a piece of text. In present scenario, different performance metrics are used to compare and evaluate the effectiveness of various machine learning algorithms. The study examines various textual properties that can be utilized to differentiate the fake and real news. Natural Language Processing techniques are used for data pre-processing which increases the accuracy of the machine learning models. Further, the extracted and preprocessed properties are used to train various ML classifiers with all possible combinations and the built models are then evaluated using various performance metrics. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimal Lot Size and Backordered Quantity Under Carbon Tax

引用

International Journal of Applied and Computational Mathematics 2024年第4期10卷 1-16页

作者： Raiya, Geetanjali Mittal, Mandeep Department of Mathematics Amity Institute of Applied Sciences Amity University Uttar Pradesh Noida 201313 India Department of Mathematics School of Computer Science Engineering and Technology Bennett University Uttar Pradesh Greater Noida India

Researchers and industry are working together to develop low carbon inventory models that comply with carbon pricing regulations while maintaining company profits. However, this task becomes more challenging when companies also face issues related to product quality imperfections. To address this issue, a new study has developed an economic order quantity (EOQ) model that takes into account carbon emission tax, defective rates, selling prices, imperfect items, scrap items and backordering. The objective of this mathematical model is reduce overall expenses, encompassing emissions-related costs. A numerical example is come up to adorn the model, based on previous data. Sensitivity analysis has also been performed to validate the model and understand system characteristics, identifying the factors that affect total emissions. © The Author(s), under exclusive licence to Springer Nature India Private Limited 2024.

关键词： Carbon tax Defective items EOQ Optimization Shortages

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：