检索结果-内蒙古大学图书馆

Annual Information Technology, Electromechanical engineering and Microelectronics Conference (IEMECON)

作者： Mukul Kumar Arpit Kumar Sharma Pramod Singh Rathore Department of IoT and Intelligent Systems Manipal University Jaipur Jaipur Rajasthan India Department of Computer and Communication Engineering Manipal University Jaipur India

ISBN: (数字)9798350387315

ISBN: (纸本)9798350387322

This research delves into the promising realm of Conditional Generative Adversarial Networks (CGANs) to explore their potential for crafting unique fashion item images. Leveraging the robust capabilities of the TensorFlow framework, along with essential tools such as NumPy and Matplotlib, we embark on a journey of model development and visualization. Our canvas of choice is the Fashion-MNIST dataset, meticulously curated to provide a rich tapestry for our CGAN to glean insights into the intricate nuances of various clothing articles. Throughout this paper, we peel back the layers of the CGAN architecture, unraveling its inner mechanisms, elaborating on the challenging yet gratifying training process, and meticulously evaluating the quality of the images it generates.

关键词： Training Deep learning Measurement Visualization Technological innovation Process control Microwave communication Generative adversarial networks Vectors Microwave imaging

来源：评论

学校读者我要写书评

暂无评论

Soiling Builds up Gradually : Soiling Semantic Segmentation

Soiling Builds up Gradually : Soiling Semantic Segmentation

引用

International Conference on Control, Automation and systems ( ICCAS)

作者： Taewoo Kim Wangheon Lee Youngbae Hwang Department of Intelligent Systems and Robotic Chungbuk National University Cheongju South Korea Department of Computer Engineering Hansei University Seosan South Korea

ISBN: (数字)9788993215380

ISBN: (纸本)9798331517939

Object detection and segmentation tasks in autonomous driving are critical not only for enhancing drivers’ convenience, but also for ensuring safety. The performance of these systems relies heavily on the cleanliness of cameras, because the contamination can lead to unpredictable and potentially hazardous behavior. Therefore, detecting foreign objects on the camera lenses is a crucial area of research. When the contamination does not cover the entire field of view, segmenting contaminated and non-contaminated areas is necessary. This segmentation allows the autonomous driving system to function effectively using the clean regions of the camera. In this study, we address the problem of soiling segmentation of fish-eye images, which are commonly used in surround view systems. We apply well-known models such as U-Net, FPN, DeepLabV3, and PSPNet. By finding the best model through extensive experiments, we show that the effect of using clean set for training and a generalization ability across different viewpoints.

关键词： Training Simultaneous localization and mapping Semantic segmentation Object detection Cameras Real-time systems Safety Reliability Autonomous vehicles Contamination

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Mesothelioma: Early Detection and Treatment

Machine Learning for Mesothelioma: Early Detection and Treat...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Bhavika Garg Tarun Jain Vijay Shankar Sharma Department of Computer Science and Engineering Manipal University Jaipur Department of IOT & Intelligent Systems Manipal University Jaipur

Mesothelioma is an extremely severe cancer that can easily transform into lung cancer. Mesothelioma diagnosis takes several months and treatment, including surgery, is expensive. Given the risk, early detection of Mesothelioma is essential for patient health, as it is connected to asbestos exposure. Various machine learning algorithms has been used in this research paper to compare with accurate results for mesothelioma detection. Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), k Nearest Neighbourhood (k-NN), and Linear Regression (LR) are some of the machine learning methods being used. For this research paper, dataset is available on UCI, called the University of California Irvine [1]. The test dataset contains 264 instances, 35 characteristics and 8 performance measures, which is used to evaluate the classifiers accuracy. The average accuracy of XGB, RF, DT, SGD, LR and Voting Classifier are 100% each. Combing all the classifiers, helps us to break through the Mesothelioma data and the creation of data driven insights to improve patient care.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gaussian Process-based Traversability Analysis for Terrain Mapless Navigation

arXiv

引用

arXiv 2024年

作者： Leininger, Abe Ali, Mahmoud Jardali, Hassan Liu, Lantao The Department of Computer Science Indiana University BloomingtonIN47408 United States The Department of Intelligent Systems Engineering Indiana University Bloomington United States

Efficient navigation through uneven terrain remains a challenging endeavor for autonomous robots. We propose a new geometric-based uneven terrain mapless navigation framework combining a Sparse Gaussian Process (SGP) local map with a Rapidly-Exploring Random Tree* (RRT*) planner. Our approach begins with the generation of a high-resolution SGP local map, providing an interpolated representation of the robot’s immediate environment. This map captures crucial environmental variations, including height, uncertainties, and slope characteristics. Subsequently, we construct a traversability map based on the SGP representation to guide our planning process. The RRT* planner efficiently generates real-time navigation paths, avoiding untraversable terrain in pursuit of the goal. This combination of SGP-based terrain interpretation and RRT* planning enables ground robots to safely navigate environments with varying elevations and steep obstacles. We evaluate the performance of our proposed approach through robust simulation testing, highlighting its effectiveness in achieving safe and efficient navigation compared to existing methods. See the project GitHub1 for source code and supplementary materials, including a video demonstrating experimental results. © 2024, CC BY.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Power Dispatch Estimation from Electric Vehicles in a Distribution System

Power Dispatch Estimation from Electric Vehicles in a Distri...

引用

International Conference on Electric Power and Energy Conversion systems (EPECS)

作者： Ganesh K. Venayagamoorthy Imanthi Kalanika Subasinghe Raj Naidoo Holcombe Department of Electrical and Computer Engineering Real-Time Power and Intelligent Systems Laboratory Clemson University Clemson SC USA Department of Electrical Electronic and Computer Engineering University of Pretoria South Africa

ISBN: (数字)9798331516963

ISBN: (纸本)9798331516970

The integration of electric vehicles (EVs) into the electric power distribution system poses numerous challenges and opportunities for optimizing energy management and system operations. Electric vehicle grid interfaces (EVGIs), essentially bidirectional power converters, allow for charging/grid-to-vehicle (G2V) and discharging/vehicle-to-grid (V2G) power transfers. A power dispatch estimation (PDE) model for V2G, based on availability of EVs in a distribution system and capabilities of the distribution system, is needed to assist in grid operations. This paper presents the development of a PDE model based on nodal power flows to capture the complex spatiotemporal dependencies inherent in G2V and V2G patterns. The hierarchical structure of a distribution system, feeder to EVGI node, is taken into consideration for PDE. Typical PDE estimation results are presented for the IEEE 34 test node feeder distribution system allocated with EVGIs.

关键词： Partial discharges Vehicle-to-grid systems operation Estimation Spatiotemporal phenomena Resource management Energy management Voltage control Vehicle dynamics Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Explainable Application Intent for Zero-Touch Networking: An Incorporation of Hypergraph and Transformer

引用

IEEE Transactions on Communications 2025年

作者： Wu, Bing Zou, Sai Liwang, Minghui Ni, Wei Wang, Xianbin Guizhou University College of Big Data and Information Engineering China National Key Laboratory of Autonomous Intelligent Unmanned Systems Department of Control Science and Engineering China Tongji University Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Shanghai China Data61 CSIRO Australia Department of Electrical and Computer Engineering Western University Canada

The autonomous interpretation of application intent (APPI) represents the primary step towards achieving closed-loop autonomy in zero-touch networking (ZTN) and also a prerequisite for intent-based networking (IBN). However, understanding APPIs and invoking the corresponding network resources require network professionals with extensive technical expertise to customize network service requests (NSRs), which presents significant challenges for the large-scale deployment of ZTN. This paper investigates an interesting problem of autonomous interpretation of APPIs for ZTN, where a novel mechanism integrating hypergraph and transformer with completeness assurance (HyperTrans-CA) is proposed. In particular, we first involve the Bayesian theory to model APPIs interpretability as maximizing the correct transition probability, where hypergraph is used to describe the complex relationship between application characteristics (e.g., scenario function, and performance) and NSRs, including network devices, virtual network functions (VNFs), and resources. Then, the hypergraph is integrated into the encoder, decoder, and attention mechanisms of Transformer, and a completeness assurance mechanism is designed to improve the prediction accuracy. The convergence of HyperTrans-CA and the corresponding convergence speed of the hypergraph-boosted Transformer in the graph search process are also analyzed. Comprehensive simulations and empirical measurements regarding industrial internet demonstrate that HyperTrans-CA can effectively explain/understand APPIs. Compared to the state-of-the-art Transformer and ChatGPT3.5 models, HyperTrans-CA improves the prediction accuracy of APPIs mapped to VNFs by 23% and 46%, respectively, while raising the prediction accuracy of VNF locations by 8.6 and 17.3 times. © 2025 IEEE.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Directed Machine Learning Approaches for Determining Alzheimer Disease

Directed Machine Learning Approaches for Determining Alzheim...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Ansh Vashist Tarun Jain Vijay Shankar Sharma Department of Computer Science and Engineering Manipal University Jaipur Department of IOT & Intelligent Systems Manipal University Jaipur

Alzheimer's is a neurogenic disease which progress into neurological disorder that primarily affects cognitive function and memory. It's a Neurodegenerative (ND) disease, characterized by the gradual deterioration of cognitive function, memory, thinking, and behaviour. There are two most common diseases among neurodegenerative diseases: (a) Alzheimer's Disease and (b) Parkinson's Disease. We used 12 classifiers on the given dataset on UC Irvine Machine Learning Repository. The machine learning algorithms were engaged to identify Alzheimer Disease. Our research results showed that the XGB Model is the one that shows the best accuracy, of 100%, of all the 12 classifiers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ovarian Cancer Prediction using Machine Learning

Ovarian Cancer Prediction using Machine Learning

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Yashika Agnihotri Tarun Jain Vijay Shankar Sharma Department of Computer Science and Engineering Manipal University Jaipur Department of IOT & Intelligent Systems Manipal University Jaipur

Ovarian cancer is the type of cancer that has the highest recurrence rate in women and poses a serious threat to women. Due to the lack of observable signs, this quiet invader often goes undetected in the beginning, leaving women susceptible to its sneaky development. Once it has advanced and its symptoms are obvious, it becomes arduous to treat. Machine learning is emerging as a ray of hope in the healthcare scene in the current era of rapid technological innovation. Machine learning provides a promising path for the early diagnosis and prediction of ovarian cancer by harnessing the power of algorithms and data analytics, perhaps turning the tide against this tough enemy. The dataset [17] comprises of 349 instances and 49 features. The goal here is to derive a model that helps in classification of instances into two classes: Benign Ovarian Tumors (BOT) and Ovarian Cancer (OC). Therefore, methodical machine learning algorithms are employed to detect ovarian cancer. Our research findings revealed that out of all the classifiers, the Random Forest Model has the highest accuracy (91.43 %). This approach is capable of accurately classifying BOT and OC and could have immense effect on diagnosis of patients, leading to better treatments and higher survival rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of Life Expectancy Rate Post Lung Surgery Using Machine Learning

Analysis of Life Expectancy Rate Post Lung Surgery Using Mac...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Shreya Tarun Jain Vijay Shankar Sharma Department of Computer Science and Engineering Manipal University Jaipur Department of IOT & Intelligent Systems Manipal University Jaipur

It has become really important for patients to know the precise results that can happen post the treatment of lung cancer or that if they have any underlying health problem which can be the cause of death post lung cancer surgery. Doctors also need to know the full detailed report of patients’ health with the risk factors that can affect their survival rate for better treatment of their patients. As such results are crucial, we need to implement such techniques which can generate the most accurate results. For such accurate analysis, we use machine learning techniques to generate better results. Several machine learning and deep learning approaches are being used to estimate the survival rate of lung cancer patients post the surgery. Examination of various health factors is used for prediction, as health factors could be significant predictors. Seven machine learning techniques that are linear regression, XGBooster, random forests, Decision Tree, KNN, SVM, voting classifier and two deep learning techniques that are ANN and BILSTM are used for analyzing performance. Analysis of accuracy has been done using F1 score, precision, and recall as measuring factors. For the analysis of outcome prediction, we have taken accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of a Mobile Monitoring Application for a Message Queuing Telemetry Transport (MQTT)-Based Struvite Fertilizer Production System

Development of a Mobile Monitoring Application for a Message...

引用

HCI and UX Conference in Indonesia (CHIuXiD), International

作者： Ilham Maulana Maya Fitria Cut Nurul Faizah Daffa Hirta Adharani Sarah Nada Jinan Rahmad Dawood Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh Indonesia Department of Electrical and Computer Engineering Interactive Intelligent Systems Reseach Group Universitas Syiah Kuala Banda Aceh Indonesia

ISBN: (数字)9798350380439

ISBN: (纸本)9798350380446

Struvite fertilizer, characterized by its slow-release qualities, is comprised of magnesium, ammonium, and phosphate and is vital for plant growth. The Integrated Laboratory Unit of Universitas Syiah Kuala (USK) has developed a prototype for struvite fertilizer production equipment, but the production process requires manual monitoring. This project seeks to create an MQTT (Message Queuing Telemetry Transport)-based mobile application for the real-time monitoring and control of struvite fertilizer production equipment. The application employs the MQTT communication protocol, known for its quick data transmission and minimal bandwidth requirements. This application incorporates sensors on the production machine, which includes a reactor, filter, and dryer, and employs an Amazon Web Service’s (AWS) IoT Core as the MQTT broker. Findings from the application’s evaluation indicate that the mobile application can efficiently monitor and control several machine components. Data transmission to MQTT topics was successful, facilitating seamless communication. Functional and integration testing demonstrated that the system operates effectively. Usability testing outcomes yielded an average score of 77.75 with a system usability scale (SUS) approach, signifying that the application possesses a satisfactory degree of usability classified within the “Grade B” category.

关键词： Production equipment Prototypes Real-time systems Mobile applications Sensors Telemetry Usability Monitoring Fertilizers Testing

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：