检索结果-内蒙古大学图书馆

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

作者： Sabiyath Fatima, N. Noor Alleema, N. Mahesh, C. Umanesan, R. Senthil, K. Santhosh Kumar, P. B.S.Abdur Rahman Crescent Institute of Science and Technology Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Department of Computer Science and Engineering Chennai India Panimalar Engineering College Department of Information Technology Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India SRM Institute of Science and Technology Department of Computer Science and Engineering Ramapuram Chennai India

ISBN: (纸本)9798331522988

Internetization has played a massive role in the rapid development and growth of the financial investment industry. due to the rapid development, there is a demand for more financial knowledge services to help make well-informed investments. Accessing and conducting investments through online financial platforms has made the field highly accessible. This has made the investment recommendation system a popular research area. Personalized recommendations will help the user make investments that are safe for their financial situation and also suit their particular needs and interests. This work proposes a method where investment recommendations are given based on three key factors. The user interest sectors, risk appetite-based clustering, and market sentiment of the stock. These factors will be calculated by the use of lasso regression, SVM, stepwise regression, generalized boosted regression, random forest, ridge regression and fuzzy clustering. Based on these three factors, the proposed method results in investment recommendations made for users that are personalized to the specific user. This allows existing investors to gain new opportunities and new investors to start investing with lower amount of risk using the information available. © 2024 IEEE.

关键词： decentralized finance

来源：评论

学校读者我要写书评

暂无评论

developing an Adaptive Security Framework for Real-Time Threat detection and Response in Cloud-Network Systems

Developing an Adaptive Security Framework for Real-Time Thre...

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Paramesh, J. Sriram, K.P. Anbalagan, E. Sasikumar, S. Vimal Kumar, M. Guru Saveetha Engineering College Department of Computer Science and Engineering Chennai India Information Technology St.Joseph's Institute of Technology OMR Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Saveetha University Chennai India Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331542344

The study is centred on examining an intelligent security system for real-time threat identification and mitigation in cloud-network systems. The more cloud computing environments are being constructed;conventional models of security do not offer optimal solutions to counteract changing cyber threats. This framework incorporates the use of sophisticated algorithms in machine learning and real-time data analysis to achieve a more proactive form of defence measures. It incorporates anomaly detection, classification algorithms and predictive analysis in the improvement of threat detection and response time. The framework also has active response mechanisms for timely deliberation on anything that may be seen to have a detrimental effect on the cloud. Analyzes reveal high levels of detection, timely responses and scalability proving the suitability of the framework to handle new threats and/or blend with existing cloud components. The findings of this study can be considered as valuable contribution to cloud security since the approach proposed in this paper can be effectively employed to enhance protection against new types of threats in specific organizational contexts. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

design, Simulation and Testing of Wave Collection and Transport System for Michelson Interferometer diagnostic

Design, Simulation and Testing of Wave Collection and Transp...

引用

2024 IEEE Microwaves, Antennas, and Propagation Conference, MAPCON 2024

作者： Sinha, Abhishek Sharma, Sonam Pathak, Surya Kumar Institute for Plasma Research Gandhinagar India HBNI Training School Complex Anushaktinagar Mumbai400094 India L D College of Engineering Ahmedabad India

ISBN: (纸本)9798350379693

A Wave Collection and Transport System (WCTS) has been designed and simulated using CST Microwave Studio to transport electromagnetic waves from tokamak hall to the Michelson interferometer (MI) system. The MI system is the diagnostic used for plasma electron temperature profile measurement on the tokamak. Simulations were carried out in the frequency range 70-170 GHz range for the transmission line components using CST microwave studio. To minimize propagation losses, oversized waveguides were chosen instead of fundamental. For selection of suitable oversized waveguide, simulations were performed in S, X and Ka band and best performing band was selected for WCTS. These oversized waveguides not only reduce propagation losses but also decrease the group delay of the propagating wave as compared to fundamental waveguide. The primary components of the oversized WCTS include waveguides, miter bends in both E and H planes, and wire-grid polarizers (WGP) to select the polarization of electromagnetic waves from the plasma. While the use of oversized waveguides significantly reduces the overall transmission line losses, it also introduces the issue of higher-order modes. The transmission line components have been designed, simulated, and experimentally validated in the laboratory, and the results have been presented. © 2024 IEEE.

关键词： Michelson interferometers

来源：评论

学校读者我要写书评

暂无评论

Towards Precise Peach disease detection: leveraging PCNN with Enhanced Activation and AFHOA Fine-Tuning

Towards Precise Peach Disease Detection: Leveraging PCNN wit...

引用

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Anitha, Cuddapah Mahaveerakannan, R. Govindaraju, Sakthi Thendral, Tamil M. Sunkesula, Haseena Department of Computer Science and Engineering School of Computing Mohan Babu University Erstwhile Sree Vidyanikethan Engineering College Andhra Pradesh Tirupati India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India School of Computer Science and Engineering Galgotias University Greater Noida India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India Rajampet Andhra Pradesh Annamayya India

ISBN: (纸本)9798350374933

Many innovations in farming and manufacturing have helped the world's seven billion inhabitants get the food they need. diseases and pests provide the greatest risk to food products because they reduce both the number besides quality of food. Various methodical methods have been devised to enhance food production while also reducing the risk of pests and illnesses affecting plants and fruits. The diagnosis of diseases is still dependent on human skill and manual labor when using these techniques. These past ten years have seen widespread usage of AI for the automation of various tasks, including harvesting in agriculture. Processing photos and identifying things using Machine learning procedures is gaining popularity. We can automate harvesting by identifying plant diseases using Machine learning algorithms;this will allow us to grow more food while cutting down on crop losses. Using the parallel convolution neural network (PCNN) suggested in this paper to detect peach disease traits-using the improved elu activation function rather than the traditional Relu activation function-we first create an image denoising procedure to mitigate the impact of the complicated background on the images. Next, the classification accuracy is enhanced by fine-tuning the hyper-parameters of PCNN using the Archerfish hunting optimizer (AFHOA) model. This method proved effective for peach disease diagnosis, as evidenced by the results of 25513 photos. The greatest detection accuracy for black spot, peach was almost 92% to 96% accordingly. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Small Intestine Cancer Prediction using deep learning: A Comparative Study of CNNs and RNNs

Small Intestine Cancer Prediction using Deep Learning: A Com...

引用

distributed Computing and High Performance Computing (dCHPC), International Conference on

作者： l Sherin Beevi P M Joe Prathap Pulimi Hanith Sai Kumar Reddy Gomasani Bhanu Sai Priya Department of Computer Science and Engineering R.M.D. Engineering College Kavaraipettai INDIA Department of Computer Science and Engineering R.M.D. Engineering College INDIA

Small bowel cancer is one of the rare tumors that often stays untreated until it has spread to a more advanced stage. Cancer is the leading cause of death in the globe. Early detection is critical for successful treatment, and machine learning algorithms have showed promise in detecting cancer at its early stages. In this article, we offer a deep learning-based technique to predicting small intestinal cancer that employs Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). We used a dataset of clinical characteristics and biomarkers from small intestinal cancer patients to train and evaluate our models. Our findings reveal that the proposed models were highly accurate in predicting small intestinal cancer, with the CNN-based model slightly outperforming the RNN-based model. We also compared our approach to other cutting-edge methodologies, and discovered that the proposed models surpassed them in terms of accuracy. Our study indicates the potential of deep learning-based approaches for predicting small intestine cancer and provides information on the relative efficacy of CNNs and RNNs. Our findings can help design more accurate and efficient cancer prediction models for small intestinal cancer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Food Image Classification Using Black Widow Algorithm and deep learning Techniques 2

Optimizing Food Image Classification Using Black Widow Algor...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Jamalpur, Bhavana Priya, Sakthi G. Venkat, S. Aarthi, R. Kavitha, S. Babu, G. Charles Department of Computer Science and Artificial Intelligence S R University Telangana Hanamkonda India Computer Science and Engineering Ramco Institute of Technology Rajapalayam India Department of ECE S.A. Engineering College Chennai India Department of ECE R.M.D Engineering College India Department of CSE Vel Tech High Tech Dr.Rangarajan Dr.Sakunthala Engineering College India Department of CSE Gokaraju Rangaraju Institute of Engineering and Technology Bachupally Telangana Hyderabad India

ISBN: (纸本)9798350383867

Food image classification is a key application of computer vision and Machine learning (Ml) devoted to mechanically classifying and labelling different food items depending on visual content seized in images. Using sophisticated Convolutional Neural Networks (CNNs) and deep learning (dl) models, this skill permits detection of different dishes, culinary creations, ingredients and raises many practical uses. From supporting nutritional choices and recipe recommendations to menu analysis and food quality control, food image detection updates procedures of food identification, providing valuable insights for users, food experts as well as food industry. Its high potential is to power detection and classification of food items provide benefits in upholding better eating habits, cooking improvement, and enhancing food creation and management procedures. This research proposed Food Image Classification Using Black Widow Algorithm and deep learning (FIC-BWOdl) model. The developed FIC-BWOdl method combines a multifaceted model starting with Contrast limited Adaptive Histogram Equalization (ClAHE) for image preprocessing, certifying improved image quality and optimum feature extraction. Extraction of features executed by utilizing Capsule Networks (CapsNet) which is famous for their capability to capture difficult classified image patterns. Classification performed via Convolutional Autoencoders (CAE), exactly classifying food images. Moreover, model controls Black Widow Optimization Algorithm (BWO) for hyperparameter tuning that enhances the act and supports it with exclusive features of a dataset. FIC-BWOdl methodology provides an important leap in food image detection that provides a strong and exact solution for automated food detection. © 2024 IEEE.

关键词： Food chemistry

来源：评论

学校读者我要写书评

暂无评论

EvauleBlock: Evaluating Answers in E-learning Applications with Enhanced Security and Intelligence through dRl and Blockchain Integration 3

EvauleBlock: Evaluating Answers in E-Learning Applications w...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Parthasarathy, R. Kiruthiga devi, M. Karthick, V. Kumar, P. Mahendran, Rakesh Kumar Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science & Engineering Chennai India Dr. Mgr Educational and Research Institute Department of Information Technology Chennai India Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350369083

Evaluating the candidate answers during online examination by a human examiner is wearisome task. Along with that, security concerns also associated in the E-learning environment in terms of false data injection and modification attacks respectively. The state of the art work, either focus on designing intelligent and robust question answering model using Machine learning (Ml)/deep learning (dl) algorithm, or designing a secure framework for E-learning environment using blockchain. To neutralize that issue, we design a secure and intelligent model for E-learning environment using deep Reinforcement learning (dRl) and blockchain methodology respectively named EvauleBlock. The EvauleBlock composed of four major processes such as data assortment, data pre-processing, intelligent answer evaluation, and blockchain storage. In data assortment stage, the training of the proposed dRl algorithm named Multi Agent deep deterministic Policy Gradient (MAddPG) is taken place by crawling the related question answering data from the various websites. Followed by, we have performed pre-processing for the candidate written answers using adequate pre-processing steps. Once the answers are pre-processed, it is then provided to the MAddPG algorithm which employs four agents for validating the candidate answers by checking the semantic, syntactic, keyword, and context similarity scoring respectively. At last, the overall scores are securely stored in the blockchain using Proof of Work (PoW) consensus algorithm. The implementation of this work is carried out using python 3.11.0 tool and performance of the proposed model are validated and compared with adequate performance metrics. The results are promising when compared to the conventional models. © 2024 IEEE.

关键词： Answer Evaluation Blockchain deep Reinforcement learning E-learning Question Answering system

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of Quantum Computing for Revolutionary Problem-Solving and Computational Advancements

Exploring the Potential of Quantum Computing for Revolutiona...

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Guru Vimal Kumar, M. Paramesh, J. Sriram, K.P. Anbalagan, E. Sasikumar, S. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Avadi Chennai India Saveetha Engineering College Department of Computer Science and Engineering Chennai India Information Technology St. Joseph's Institute of Technology OMR Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331542344

Quantum computing is a model of computing a new approach to perform and solve computational problems and comes up with amazing advantages such as exponential speed-up of specific tasks that lead to a revolution of industries. In this study, Quantum Computing potential is discussed in multiple fields - drug discovery and optimization, and quantum machine learning contrasted with traditional methods based on the running time, accuracy, and scalability of quantum and classical algorithms. Applying several quantum algorithms to molecular simulation, optimization problem, and image classification data sets, quantum algorithms solved problems with at least 70% less number of iterations and at worse the same accuracy as classical methods. For instance, researchers noted that quantum neural networks performed better than classical networks in image recognition. The quantum algorithms in this study were implemented and simulated using IBM Qiskit, d-Wave's Ocean SdK and TensorFlow Quantum. Based on the literature reviewed;it was established that quantum computing has potential to revolutionalise endeavours in drug design, cryptography and artificial intelligent applications. While there are issues in qubit stability quantum decoherence, errors and other related complications, it is predicted that all these problems will be solved by qubit stability and quantum error correction shortly and therefore, realistic, scalable quantum systems are in the next few years. Further research is required on the quantum technology one which may bring a revolution in the way different industries solve their problems. © 2024 IEEE.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

design and Analysis of Graphene Based Tunnel Field Effect Transistor with Various Ambipolar Reducing Techniques

引用

computers, Materials & Continua 2023年第7期76卷 1309-1320页

作者： Puneet Kumar Mishra Amrita Rai Nitin Sharma Kanika Sharma Nitin Mittal Mohd Anul Haq Ilyas Khan ElSayed M.Tag El din Department of Electronics and Communication Engineering G L Bajaj Institute of Technology and ManegmentGretear NoidaIndia Department of Electronics and Communication Engineering Chandigarh UnievrsityMohaliPunjabIndia Department of Electronics and Communication Engineering NITTTRChandigarhIndia University Center of Research&Development Chandigarh UniversityMohali121102India Department of Computer Science College of Computer and Information SciencesMajmaah UniversityAl-Majmaah11952Saudi Arabia Department of Mathematics College of Science Al-ZulfiMajmaah University11952Al-MajmaahSaudi Arabia Electrical Engineering Department Faculty of Engineering&TechnologyFuture University in EgyptNew Cairo11835Egypt

The fundamental advantages of carbon-based graphene material,such as its high tunnelling probability,symmetric band structure(linear dependence of the energy band on the wave direction),low effective mass,and characteristics of its 2d atomic layers,are the main focus of this research *** impact of channel thickness,gate under-lap,asymmetric source/drain doping method,workfunction of gate contact,and High-K material on Graphene-based Tunnel Field Effect Transistor(TFET)is analyzed with 20 nm *** modelling and electrical characteristic performance have been simulated using the Atlas device simulator of SIlVACO TCAd with user-defined material syntax for the newly included graphene material in comparison to silicon carbide(SiC).The simulation results in significant suppression of ambipolar current to voltage characteristics of TFET and modelled device exhibits a significant improvement in subthreshold swing(0.0159 V/decade),the ratio of Ion/Ioff(1000),and threshold voltage(-0.2 V with highly doped p-type source and 0.2 V with highly doped n-type drain)with power supply of 0.5 V,which make it useful for low power digital applications.

关键词： Graphene tunnel field effect transistor(TFET) band to band tunnelling subthreshold swing

来源：评论

学校读者我要写书评

暂无评论

Innovative data Encryption Techniques using AI for Wireless Sensor Actuator Network Security 2

Innovative Data Encryption Techniques using AI for Wireless ...

引用

2nd International Conference on distributed Computing and Optimization Techniques, ICdCOT 2024

作者： dharmateja, M. Rama, Prabha K.P. Asha, N. Nithya, P. lalitha, S. Manojkumar, P. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Arunai Engineering College Department of Computer Science and Engineering Tamil Nadu Tiruvannamalai India Bannari Amman Institute of Technology Department of Electrical and Electronics Engineering Tamil Nadu Sathyamangalam India

ISBN: (纸本)9798350382952

Wireless Sensor Actuator Networks (WSANs) are sensitive to cyber threats due to present static encryption techniques. Adaptive security methods are required in WSAN settings to reduce evolving dangers and maintain data integrity. The paper introduces a novel method for encrypting WSAN data using AI and machine learning. long Short-Term Memory (lSTM) networks process data, Genetic Algorithms (GAs) optimize encryption, and Isolation Forests detect threats in real-time. The proposed system achieved remarkable performance, with scores of 98% data integrity, 96% error repair, and 95% threat detection accuracy. Encryption rates reach their max at 200 Mbps, with optimal resource usage (30% CPU, 25% RAM) and a 5% false positive rate. The proposed AI-driven security architecture improves data integrity, encryption speed, and overall security efficacy in WSANs, surpassing existing methods. The paper overcomes the limitations of static encryption methods and proposes a proactive protection mechanism against developing cyber threats, making a substantial contribution to WSAN security improvement. © 2024 IEEE.

关键词： Cryptography

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：