检索结果-内蒙古大学图书馆

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

The Impact of Heat Treatment and Surface Treatment on Thermal Conductivity of Heat Sinks Made of Aluminium die Casting Alloys

引用

Journal of Harbin institute of technology(New Series) 2024年第4期31卷 34-41页

作者： rajesh Kumar Manickam dilip raja Narayana Department of Mechanical Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and TechnologyChennai 600001Tamil NaduIndia

This research contributes to understand the thermal management capabilities of Plate Fin Heat Sinks(PFHS)fabricated from *** uniqueness in this study is that the heat sinks were exposed to abrasive blasting,heat treatment,and graphene coating,and a full evaluation of the influence of the aforementioned treatments on the thermal management capacities of PFHS was *** PFHS is compared with 1)abrasive blasted and graphene coated heat sink,and 2)heat treated and graphene coated heat *** assess the thermal efficiency of the PFHS variants,a dedicated experimental set up was meticulously *** is noteworthy that a junction temperature of 60℃was assumed as the reference point for the *** results revealed that the charging cycle time which denotes the time required attaining the junction temperature,increased 1.3 times for the sample being abrasive-blasted at 0.5 MPa pressure and graphene-coated for 0.5 mm when the maximum heat input of 45 W is *** low heat input of 15 W is evaluated,the results revealed that there is no significant difference in charging cycle when compared to the untreated heat *** charging cycle time increased 2 times for the sample which is heat-treated at 450℃and graphene-coated for 0.5 mm at heat input of 15 *** finding unequivocally underscores the heightened capacity of the heat treated and graphene coated PFHS made of AlSi10Mg to withstand elevated junction temperatures.

关键词： PFHS abrasive blasting heat treatment graphene

来源：评论

学校读者我要写书评

暂无评论

A Circular Slotted Wide Band Antenna for Sub 6 GHz Wireless Applications 3

A Circular Slotted Wide Band Antenna for Sub 6 GHz Wireless ...

引用

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

作者： Chinnathambi, Murugan Thandapani, Kavitha Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Electronics and Communication Department Chennai India

ISBN: (纸本)9798350369083

This paper introduces a circular slotted antenna tailored for 5G applications, resonating within the 4.4 to 7.25 GHz frequency band. Fabricated on a 1.6 mm Fr4 substrate with a dielectric constant of 4.4 and a tangential loss of 0.02, the antenna boasts dimensions of 22 mm x 15 mm. Performance analysis reveals gains of up to 4 dBi and remarkable efficiency levels of up to 85% across the operational spectrum. The compact size and impressive performance metrics make it a compelling choice for modern wireless communication systems. The antenna's broadband characteristics enable it to cover a significant portion of the 5G frequency range, ensuring compatibility with emerging communication standards. Moreover, its efficient design and high gain capabilities contribute to improved signal transmission and reception, enhancing overall network performance. Through extensive analysis, this research underscores the antenna's suitability and efficacy for 5G applications. The results affirm the circular slotted antenna as a promising solution to address the evolving demands of 5G technology. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Cluster Based routing Protocol for Wireless Sensor Network

An Intelligent Cluster Based Routing Protocol for Wireless S...

引用

2024 International Conference on recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence, rAEEUCCI 2024

作者： Pal, debashish Subramanya Kasi, M. Kumari, Khushbu Harika, P. R&D Institute of Science and Technology Vel Tech Rangarajan Dr. Sagunthala Dept. of ECE Chennai India

ISBN: (纸本)9798350354539

This paper documents efforts to reduce the energy usage of sensor nodes in a wireless sensor network (WSN). Multiple studies have shown the advantages of conserving energy in nodes, and cluster-based routing is a notable outcome of this. This work use fuzzy logic to choose cluster heads (CHs). The simulation results of the design are compared to other well-known protocols in this category, considering the number of rounds needed for the first node to fail and the network's lifespan. The efficacy of the proposed architecture is exemplified by this comparative analysis, perhaps generating further enthusiasm for the development of more efficient methodologies. © 2024 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Efficient Network resource Management for Improving radio Access Through Machine Learning Approach in 5G Networks

引用

Journal of The Institution of Engineers (India): Series B 2025年第1期106卷 207-215页

作者： Coumar, S. Oudaya Surender, r. Department of ECE Vel Tech Rangarajan Dr. Sagunthala R &D Institute of Science and Technology Tamil Nadu Avadi Chennai600062 India Department of ECE Sathyabama Institute of Science and Technology Chennai India

Network resource management is one of the vital factors in recent dynamic technological computing paradigm as there is a significant degradtion in resource utilization. Network resources include networking, management systems and management support organizations. The major roles are to manage tasks, schedule resources and manage networks. It needs new challenges and requirements, making it more difficult to accomplish the intended objectives. Further, it involves complexity for mobile operators to devise solutions that are flexible, dynamic, cost-effective and intelligent with conventional wireless network. These issues can be addressed by emerging services of 5G (5th Generation) technology incorporating machine learning technique to enhance the performance within a real-time *** work in this paper highlights the overview of the requirements, key technologies, and challenges associated with 5G cellular networks. Further machine learning techniques like long short term memory (LSTM), deep belief network (dBN), hybrid genetic algorithm (HGA) are incorporated in 5G networks and addressing 5G’s challenges using machine learning. The proposed work employing machine learning algorithms will show that the performances of resource management is superior than existing methods. © The Institution of Engineers (India) 2024.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Performance of Spatial domain BGM Filtering and MS-SVM Classifier on Breast Cancer X-ray Images Using CNN Architecture

Performance of Spatial Domain BGM Filtering and MS-SVM Class...

引用

2024 IEEE International Conference on Intelligent Signal Processing and Effective Communication technologies, INSPECT 2024

作者： Mahalakshmi, V. Sasikala, G. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Electronics and Communication Engineering Chennai India

ISBN: (数字)9798350379525

ISBN: (纸本)9798350379525

Over the decades, breast cancer has become one of the epidemic diseases among women throughout the universe that causes more mortality. despite the evolution of many screening technologies, the mammogram is still considered the predominant screening tool to identify breast cancer at an earlier stage. As artificial intelligence (AI) continues to advance, many research investigations have been conducted into the automation process of breast cancer detection. This study shows how well a Markovian sample support vector machine (MS-SVM) classifier and a bilateral guided median (BGM) spatial filter work in a simulation model on a public x-ray dataset for breast cancer. The proposed MS-SVM classifier is used to train the breast lesion classification model as healthy or unhealthy tissues with the image features that have been extracted using the 5-layer convolutional neural network (CNN). In addition, for the evaluation of the MS-SVM classifier, traditional machine learning (ML) approaches such as SVM (support vector machine), rF (random forest), dT (decision tree), and NB (naive bayes) were used to analyze the classification metrics. Contrary to CNN and traditional ML classifiers, the proposed hybrid approach has improved accuracy by 0.987 with an increase in overall model performance of 5%, and the model training duration has been reduced to 157.27 seconds on average. © 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

Transforming diabetes Care with Predictive Machine Learning techniques 4

Transforming Diabetes Care with Predictive Machine Learning ...

引用

4th International Conference on Power, Energy, Control and Transmission Systems, ICPECTS 2024

作者： Mariammal, G. Jasmine, r. Megiba Siva rama Lingham, N. Poongothai, E. Prema, S. Sai Charan, S. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Chennai India Ponjesly College of Engineering Nagercoil India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India

ISBN: (纸本)9798331508845

diabetes mellitus is a chronic metabolic disorder characterized by elevated blood sugar levels, affecting millions of individuals worldwide. Early detection and management of diabetes are crucial in preventing complications and improving patient outcomes. In recent years, machine learning techniques have shown promise in predicting diabetes risk based on various factors such as demographic information, medical history, and lifestyle habits. Verticaling through a not-too-well designed case study - This paper is an extensive examination and comparison of different ML techniques for diabetes prediction. It goes through the methodologies, datasets, features, performance metrics and challenges of current models that are based on machine learning. In addition, understand strengths and weaknesses of all the algorithms- SVM, decision Trees, random Forests, Logistic regression etc. Here the logistic regression algorithm is used to develop a predictive model for diabetes based on demographic and clinical features. After preprocessing the data, including handling missing values and scaling numerical features, trained a logistic regression model using a portion of the dataset. The model achieved a high accuracy of 90% on the testing set, indicating its effectiveness in distinguishing be- tween diabetic and non-diabetic individuals. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Virtual Medical Assistant System for diseases detection using Machine Learning 2

Virtual Medical Assistant System for Diseases Detection usin...

引用

2nd International Conference on Smart technologies and Systems for Next Generation Computing, ICSTSN 2023

作者： Kanimozhi, J. Mohanasuganthi, N. Jaffrin, Lijetha C Preethi, G. Ayshwariya, S. Abi Dept of CSE Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Dept of Information Technology Chennai India

ISBN: (纸本)9798350348002

Health is very important for human lives. The health sector is growing day by day. Nowadays, due to information and communication technology, the health sector has grown immensely. Therefore, the virtual medical assistant system is developed by combining the machine learning algorithm to become part of this growth. The Virtual Medical Assistant System predicts heart disease according to the health parameters like age, height, weight, BMI, and hypertension given by the user. For pattern recognition and classification problems, K-Nearest Neighbor (k-NN), back-propagation neural networks, Naive Bayes, and Support Vector Machines (SVM) algorithms are employed to implement the system. The SVM classifier performs the best for the classification problems, and XGBoost is combined for feature extraction purposes to develop new feature combinations for training the SVM model. And from the experimental analysis, the accuracy obtained for SVM is 90.S%, but for others it's less. This proposed system checks, whether a person is affected by the disease or not and recommends the right specialist for that disease, which is a difficult process nowadays. So it saves the patient both time and money. This work is to provide a virtual medical assistant that can analyze symptoms, predict diseases, and recommend a specialized doctor. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Comparative Performance Study on the Time Intervals of Hybrid Brain–Computer Interface Signals

引用

SN Computer science 2023年第6期4卷 1-9页

作者： Shelishiyah, r. Thiyam, deepa Beeta Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai – 62 India

Acquiring motor events with EEG and fNIrS have proven to be the most convenient and cost effective method. EEG explains an event with respect to a depolarization occurring when a task was done giving information on the instance of brain’s response to a certain stimuli. On the other hand, fNIrS interprets the same as rise in metabolic activity in a certain part of the cerebral cortex, explaining the location which is activated by the stimuli. The results from these single modalities compliment resulting in lower classification accuracy. The combined modalities for brain signal acquisition provide a better classification accuracy as compared to single modality, with a reduced number of features since both spatial and temporal information is achieved. In this study, we used simultaneous data from EEG and fNIrS modalities. This combination when used for motor tasks, especially hand movements and arm movement shows an improved classification since the arm and hand spatially lie adjacent to each other and it is challenging to use EEG alone to resolve the right/left arm/hand movement. The current work shows that choice of time intervals of task performance can give better results with second and higher order features taken using Thin ICA instead of taking the entire task data. This would not only reduce computational load, but will also improve the command generation time in future. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： EEG fNIrS Hybrid BCI Kurtosis SVM Thin-ICA Time slicing

来源：评论

学校读者我要写书评

暂无评论

A Vision-Based Traffic Accident Analysis and Tracking system from Traffic Surveillance Video 3

A Vision-Based Traffic Accident Analysis and Tracking system...

引用

3rd IEEE International Conference on Intelligent techniques in Control, Optimization and Signal Processing, INCOS 2024

作者： Anjana, P. Nallasivan, G. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Avadi Chennai India

ISBN: (纸本)9798350361186

Traffic accidents pose significant challenges to road safety and transportation management worldwide. Timely and accurate analysis of these incidents is crucial for effective response and mitigation. This paper presents a novel VisionBased Traffic Accident Analysis and Tracking System designed to detect, analyze, and track traffic accidents from surveillance videos using advanced image processing techniques. recent research methodology has unlimited in realizing the object trajectories of vehicle accident connected information detecting and take out the features relationships. The proposed research paper recommends a road traffic accident tracking systems that assist to establish whether every video sequence demonstrates mishap by producing and considering vehicle object trajectories using Vehicle Influence Location Generator and CNN classifier. In the proposed system, the vehicle influence location generator includes three parameters: vehicle object trajectories the distances between vehicles and accident analysis. First parameter, vehicle portions are identified by rectangle bounding box in green colour. The second parameter, vehicle portion centre positions are represented by dots using region of Interest (rOI). The final parameters, the distances between previous vehicle frame and current vehicle frame are represented by points. The proposed system considered threshold value for distance calculation and update the values. Finally, the opportunity of a disaster is characterized by red circles. A CNN will be used to analyze the accident from the Vehicle Influence Location Generator produced by vehicle object trajectories. The proposed model was trained using CAdP dataset in the training and testing stage, and it was able to obtain an estimated 96.5 % accuracy rate in overall proposed traffic accident detection. © 2024 IEEE.

关键词： Location

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：