检索结果-内蒙古大学图书馆

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Charaan, r.M. dilip Vimala Ithayan, J. Sankar, M. Chithambaramani, r. Sivaprakash, P. Marichamy, d. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science & Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala Institute of Science and Technology Department of Cse Chennai India Vel Tech Rangarajan Dr. Sagunthala Institute of Science and Technology Department of Ece Chennai India

ISBN: (纸本)9798331504403

Neural networks that are inspired by the way a human brain is structured, are known as artificial neural networks represent a unique class of machine learning algorithms. These algorithms allow artificial neural networks to acquire from data, and make resolutions based on the outcome, just like humans do. Non-linear data models, which have a whole load of variables and inputs, can predict new patterns. Artificial neural networks are already leveraged in everything from medical diagnoses to speech recognition as well as the ever-growing field of machine translation. There are multiple processes involved in the deep learning methodology that the method suggests for classifying bipolar disease. First, clinical and demographic data such as the sample's age, gender, symptom severity, and medication history would be included in the dataset of bipolar disorder patient samples and control samples. The dataset would next undergo preprocessing to remove any outliers or missing values. In the meantime, standardization and normalization would be applied to the data to ensure that each variable is on a consistent scale. data scientists may also decide to use feature selection to determine which variables are most useful for overall optimization for classification goals. In this proposed system accuracy is better as compared to the remaining conventional models. This makes it easier for us to select the elements that are most crucial to making our part a real feature. The two models ANN are the final features. Findings demonstrate that deep learning models, like as artificial neural networks (ANNs), are effective in treating neuroinformatics illnesses since datasets are readily available. When it comes to public relations, moods, and the dataset, the deep learning model predicts the correct classes with more precision. A popular application of ANN involves approximating a random function, thereby providing an inexpensive way to get to various statistics characterizing its distrib

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Application Of Some Topological Indices In Nover Topologized Graphs

引用

Neutrosophic Sets and Systems 2023年 55卷 451-470页

作者： Muthumari, G. devi, r. Narmada Department of Mathematics Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Chennai India

In this paper Nover top Z1 and Z2 index and Nover top H − index, rd − index, GA − index, CON − index are investigated and some of the related theorems are *** indices are also calculated for some specific types of Nov... 详细信息

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Historical Strategies Flow detection for Organizations using Machine Learning

Historical Strategies Flow Detection for Organizations using...

引用

2024 International Conference on Integration of Emerging technologies for the digital World, ICIETdW 2024

作者： dilip Charaan, r.M. Sankar, M. Sivaprakash, P. Vimala Ithayan, J. Chithambaramani, r. Marichamy, d. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science & Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala Institute of Science and Technology Department of ECE Chennai India Vel Tech Rangarajan Dr. Sagunthala Institute of Science and Technology Department of CSE Chennai India

ISBN: (纸本)9798331541170

Companies hire a wide variety of strategies to attain their enterprise dreams, which could embody diverse elements in their operations. The venture investigates the feasibility of predicting a company's future profitability using machine studying based on ancient strategic facts. With the emergence of gadget gaining knowledge of and information mining in current years, new thoughts and methods have emerged in the detection of bizarre network flows for monetary statements. This explores the application of device studying techniques, especially random forest and selection tree algorithms, for historic method waft detection in organizations. It targets to increase a robust methodology to research historical statistics and perceive patterns that screen strategic shifts or traits over time. By leveraging random woodland and choice tree algorithms, which are well-perfect for class responsibilities and function selection, the have a look at seeks to offer precious insights for strategic choice-making. The proposed technique involves preprocessing the statistics, choosing applicable functions, and schooling the ML models to come across historical method flows. The outcomes are predicted to beautify underneath-status of ways businesses evolve their strategies through the years, thereby supporting in enhancing strategic making plans and decision-making procedures. The model's powerfulness is classified on a checking out set to decide its accuracy in forecasting profitability, and discover styles which might be related to future earnings increases. It demonstrates the capability of device getting to know to transport past surely detecting abnormalities in monetary statements. By reading a broader variety of ancient strategic information, the performance won is above 85% to 95%. This deeper information empowers businesses to make informed choices about aid allocation. This approach offers several benefits over traditional forecasting techniques. The version can probably help ag

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

design and development of Efficient Feeding Network Structure for Patch Antenna Array Modules in UAV Communication Applications

Design and Development of Efficient Feeding Network Structur...

引用

International Conference on VLSI, Signal Processing, Power Electronics, IoT, Communication and Embedded Systems, VSPICE-2022

作者： Bharati, Chandravijay Prasanna, r. Balasubramanian, E. Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India Department of Mechanical Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India

ISBN: (纸本)9789819944439

This article focused on the development of microstrip patch antenna with linear and planar array distribution structures. Ansoft HFSS electromagnetic simulation software was used to analyze the radiation and reflection parameter of the designed element. Initially, single element antenna was realized and further 1 × 2, 2 × 2, and 1 × 4 array structures were analyzed with a due consideration of two different substrate materials such as duroid-5880 and Fr-4. 1 × 4 array antenna with duroid-5880 offers highest gain of 14.12 dB. To validate the design concept, 1 × 2 array antenna was fabricated. S11 parameter was measured using a vector network analyzer and it has downward frequency shift by 54.5 MHz as compared to simulated results. The radiation characteristic of the antenna was measured on anechoic chamber, and the E/H plot reveals that antenna is unidirectional. Measured gain is enhanced by 7.82 dB as compared to simulated results. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Secure and reversible Medical Image Watermarking for E-Healthcare Applications 6

Secure and Reversible Medical Image Watermarking for E-Healt...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Nandhini, K. rajkumar, r. Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522667

E-healthcare and mobile healthcare technologies have become increasingly important for efficient healthcare delivery in recent years due to the pandemic's needs for real-time data interchange. The electronic transfer of patient health records, including imaging reports, is made possible by the growing public networks connecting diagnostic labs and hospitals. However, this strategy is unsafe since outside attacks on public networks can expose private health information, leading to inaccurate diagnoses and treatments. To overcome such challenges, methods such as Medical Image Watermarking (MIW) and data encoding are employed to safeguard patient identities and identify instances of tampering. data security is crucial because outsourcing patient records and medical reports to servers exposes them to modification and illegal access. This study presents a new reversible watermarking technique with a large payload and minimal computational expenditure. It divides the medical image into a Border region (Br) and a Non-Border region (NBr). A pseudorandom key encrypts the Electronic Patient record (EPr), which is incorporated in the image after the NBr has been upscaled using Neighbor Mean Interpolation (NMI). The technique, which incorporates both local and global tamper detection, produces remarkable results with robustness against a range of threats and an average PSNr of 61.14 dB with average embedding and extraction times of 0.88 and 0.83 seconds, respectively, the approach is incredibly secure and effective, demonstrating its efficacy in comparison to contemporary, widely used techniques. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Enhancing Early diabetes detection using Ensemble Machine Learning Models for Improved Prediction and Patient Care 5

Enhancing Early Diabetes Detection using Ensemble Machine Le...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Shanthini Watson Benjamin, Minu Inba Syed, Arshad Vamsi, Tamma raja Kumar, P.S.d.Sai Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Department of Computer Science & Engineering Chennai India

ISBN: (纸本)9798331530013

Millions of individuals worldwide suffer from diabetes, a chronic condition that must be detected early to avoid major health issues like kidney failure, nerve damage, and heart disease. By using ensemble technique which combines machine learning (ML) approaches and evaluate the outputs and generates final prediction, then diabetes can be predicted more precisely. random Forest, Support Vector Machine (SVM), and Logistic regression, were the machine learning techniques and Voting Classifier is the ensemble classification model which were examined in this study. The study evaluated these model's ability to predict diabetes using datasets such as the Pima Indian diabetes dataset. Through the integration of Support Vector Machine (SVM), random Forest, and Logistic regression algorithms using a Voting Classifier, proposed model achieves an accuracy of 79%. This ensemble approach demonstrates superior performance compared to individual algorithms, with improved precision (0.81) and recall (0.78). It is identified that Predictive accuracy is found to be highly dependent on key parameters including glucose, BMI, and age with correlation coefficients of 0.47, 0.29, and 0.24 respectively. This method showed that combining multiple ML algorithms can significantly enhance diabetes diagnosis and care in addition to improving prediction capabilities. In the end, the study emphasizes how machine learning can completely change the way diabetes is treated and stresses how crucial it is to keep developing and using these technologies in order to improve patient outcomes. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Navigating Space: A ddPG-Based Approach to Autonomous Satellite Navigation 10

Navigating Space: A DDPG-Based Approach to Autonomous Satell...

引用

10th International Conference on Electrical Energy Systems, ICEES 2024

作者： Alex david, S. Appala, Charan Balurgi, Shreya Nagisetty, Anil Kumar Manam, Anusha Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350353778

This study developed a modern autonomous navigation system using proximity and accelerometer sensors, along with deep reinforcement learning algorithms. The system ensures safety by providing real-time data on obstacles and distance through proximity sensors, forming the basis for quick decision-making. Accelerometers measure movement precision and navigation orientation, determining the necessary distance and force for maneuvers. deep reinforcement learning, using ddPG algorithms, enables the system to learn and make decisions independently. The system can navigate, avoid obstacles, and seek cover autonomously, promoting the development of more independent systems. © 2024 IEEE.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

A novel approach to utilize recycled concrete aggregates as landfill liner

Waste Management Bulletin

引用

Waste Management Bulletin 2023年第1期1卷 39-48页

作者： Anstey Vathani, T. Logeshwari, J. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai 6000062 India

demolition wastes are produced in huge quantity. Generally, they are used in the construction field as replacement for normal aggregate, pavement, roadways, curbs, embankment, etc. still there are plenty of quantity to be used for various purposes. Landfill is a place where huge quantity of material is required as cover to protect the ground from contamination. In this paper optimal utilization of recycled Coarse Aggregate (rCA) as a landfill layer is explored. It was found that rCA lacks adsorbent capacity, in order to address the issue various chemicals were added to induce adsorbing capacity in the rCA. The pH observation, lucidity and color were analyzed to assess the adsorbent property of rCA. In this paper a study on various adsorbents such as activated carbon, silica gel powder, zeolite, sodium chloride, calcium sulphate, calcium chloride that induces adsorbing characteristics to rCA was studied. The pilot setup design consists of a layer of rCA, paper pulp, adsorbents and the unfiltered leachate. The setup was observed for the performance of the adsorbents when added with rCA. The study concluded that the performance of activated carbon, zeolite and sodium chloride was Congenial when compared to silica gel, calcium chloride and calcium sulphate. © 2023 The Authors

关键词： Adsorbents Liner Municipal Solid Waste recycled Coarse Aggregate (rCA)

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Traffic Prediction in Urban Area using Convolutional Temporal Network System 6

Spatio-Temporal Traffic Prediction in Urban Area using Convo...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Priya, K. Omkar, K. Naresh, r. Venkatesh, K. Dept. of Artificial Intelligence and Data Science Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (纸本)9798331522667

Traffic prediction in urban areas is essential for smart city applications, enabling efficient transportation management, reduced congestion, and improved quality of life. Spatiotemporal traffic prediction is particularly challenging due to complex spatial and temporal dependencies in traffic data. This study introduces a Convolutional-Temporal Neural Net- work System (CTNS) model that combines Convolutional Neural Networks (CNNs) and recurrent Neural Networks (rNNs) to capture spatial and temporal features simultaneously for more accurate traffic forecasting. CNNs are employed to learn spatial correlations between different locations in the urban area, while rNNs, specifically Long Short-Term Memory (LSTM) networks, capture the sequential dependencies in temporal traffic patterns. Using real-world traffic data, the hybrid CTNS model demonstrates superior performance in accurately predicting traffic flow compared to traditional models. This approach highlights the potential of deep learning architectures for enhancing the accuracy of traffic predictions, which is critical for urban planning and intelligent transportation systems. Extensive experiments on real-world urban traffic datasets validate the model’s ability to achieve high accuracy, scalability, and robustness in handling complex spatio-temporal interactions. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Ensemble of deep Learning Enabled Tamil Handwritten Character recognition Model 2nd

Ensemble of Deep Learning Enabled Tamil Handwritten Characte...

引用

2nd International Conference on Big data, Machine Learning, and Applications, BigdML 2021

作者： Thanga Selvi, r. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (纸本)9789819934805

recently, digitalization of handwritten characters has become a hot research topic and finds applicability in different domains. At the same time, recognition of Tamil handwritten characters is a tedious task compared to other languages. Therefore, this paper presents a new ensemble deep learning-based Tamil handwritten character recognition (EdL-THCr) model. The EdL-THCr model recognizes and classifies the Tamil handwritten characters. In addition, data preprocessing approach is involved using bilinear interpolation technique to normalize the images. Besides, an ensemble of capsule network (CapsNet) and VGGNet models take place for feature extraction process. Finally, softmax layer is employed to classify the Tamil characters in an effective way. A comprehensive experimental analysis is carried out on benchmark dataset, and the results portrayed the better performance of the EdL-THCr technique. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Character recognition

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：