检索结果-内蒙古大学图书馆

Efficient Lung Cancer Detection Based on Support Scalar Vector Feature Selection with Fuzzy Optimized-Multi Perceptron Neural Network Using Natural Language Processing

Efficient Lung Cancer Detection Based on Support Scalar Vect...

引用

Sustainable computing and Smart Systems (ICSCSS), International Conference on

作者： Jabir. K S. Kamalakkannan J. Anita Smiles Department of Computer Science School of Computing Sciences Vels Institute of Science Technology & Advanced Studies(VISTAS) Chennai India Department of Information Technology School of Computing Sciences Vels Institute of Science Technology & Advanced Studies(VISTAS) Chennai India Department of Computer Applications SRMIST Chennai India

ISBN: (数字)9798350379990

ISBN: (纸本)9798350391558

Lung cancer is one of the most frequent types of cancer worldwide, and it has a high fatality rate. To improve survival chances and ensure a successful treatment, early identification of lung cancer is essential. The rapidly developing artificial intelligence discipline of Natural Language Processing (NLP) has great promise for transforming the understanding, identification, and management of lung cancer. Previously, NLP-based lung cancer prediction models may not always produce accurate results, as they rely on complex algorithms to analyze text data. Errors in language processing or interpretation can lead to incorrect predictions and potentially harmful decisions. This study suggests employing Fuzzy Optimized -Multi Perceptron Neural Network (FOMPNN) for lung cancer detection based on NLP and the Relative Support Scalar Vector Feature Selection (RSSCVFS) method for optimal attribute selection. To begin with, preprocessing involves finding null and missing values, and textual summaries based on stemming and tokenization. Then, the Semantic Lexicon-Based Approach (SLBA) is used to find the sentiment score. Furthermore, the sentiment score of each word in the medical summary can be added up to get the overall sentiment of the text. Based on dictionary terms, feature outcomes are added to patient records. Similar generalization patterns based on Linguistic Subset Pattern Mining (LSPM) are used to produce corresponding feature patterns. The RSSCVFS method is used to pick features based on their significance to minimize the feature dimension of the illness effect rate. To classify the risk of lung cancer, the FOMPNN is finally utilized to test the feature's weight. The proposed method proficiently produces better performance than other methods.

关键词： Fuzzy logic Accuracy Uncertainty Neural networks Lung cancer Predictive models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Improving Alpha-Beta Pruning Efficiency in Chess Engines

Improving Alpha-Beta Pruning Efficiency in Chess Engines

引用

IT Innovation and Knowledge Discovery (ITIKD), International Conference on

作者： Rekha R Nair Tina Babu S Kishore K Pavithra S G Sumana Department of Computer Science and Engineering Alliance School of Advanced Computing Alliance University Bengaluru India Department of Computer Applications Nitte Institute of Professional Education Nitte (Deemed to be University Mangalore India Department of Computer Applications Dayananda Sagar University Bengaluru India

ISBN: (数字)9798350355468

ISBN: (纸本)9798350355475

Alpha-Beta Pruning is a critical optimization technique in chess engines, helping them make fast, accurate decisions by reducing unnecessary calculations. This paper focuses on enhancing its efficiency to improve search depth and speed with-out compromising accuracy. This investigation examines current challenges in traditional implementations, such as inefficiencies in move ordering and redundant computations, especially in complex game scenarios. The proposed innovative strategies include dynamic move ordering powered by machine learning and improved transposition table management. These techniques streamline the pruning process, ensuring the most promising moves are evaluated first and avoiding repetitive calculations. Adaptive depth control is explored to make the algorithm more responsive to the game's context. Extensive testing on various chess positions demonstrated clear improvements in pruning efficiency. The enhanced algorithm can analyze deeper game trees with reduced computational costs, making chess engines faster and smarter. These advancements not only benefit chess engines but also have broader implications for Artificial Intelligence (AI) systems requiring efficient decision-making in dynamic environments. Improved Alpha-Beta Pruning methods make chess engines smarter and faster, allowing them to analyze deeper strategies while using less computing power.

关键词： Technological innovation Accuracy Machine learning algorithms Heuristic algorithms Games Machine learning Aerodynamics Engines Optimization Testing

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient and Privacy-Preserving Hierarchical Federated Learning for Distributed Edge Network 5th

Towards Efficient and Privacy-Preserving Hierarchical Federa...

引用

5th International Conference on Blockchain and Trustworthy Systems, BlockSys 2023

作者： An, Ningyu Liang, Xiao Zhou, Fei Wang, Xiaohui Li, Zihan Feng, Jia Guan, Zhitao State Grid Laboratory of Grid Advanced Computing and Applications State Grid Smart Grid Research Institute Co.Ltd Beijing100209 China School of Control and Computer Engineering North China Electric Power University Beijing102206 China State Grid Zhejiang Electric Power Company.Ltd Hangzhou310007 China

ISBN: (纸本)9789819981007

Federated learning is a promising paradigm that utilizes widely distributed devices to jointly train a machine learning model while maintaining privacy. However, when oriented to distributed resource-constrained edge devices, existing federated learning schemes still suffer from heterogeneity challenge. Hierarchical federated learning divides devices into clusters based on their resources to enhance training efficiency. In addition, there are also security concerns such as the risk of privacy leakage during the interactions intra and cross the layers. In this paper, we propose PHFL, a Privacy-Preserving Hierarchical Federated Learning Scheme, which includes a personalized task assignment protocol and a heterogeneous-friendly aggregation scheme, so as to achieve an efficient and low-cost training for resource-constrained edge devices. To address the heterogeneity challenge, we combine synchronous and asynchronous aggregation, and design different aggregation weights for device differences. On top of that, a privacy-preserving scheme based on threshold homomorphic encryption is designed to accommodate the privacy requirements of the proposed hierarchical federated learning scenario. The security analysis and performance evaluation demonstrate that this approach improves model generalizability and learning efficiency with acceptable overhead, while also providing privacy protection. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Image Analysis to Track Vehicles 2

Deep Learning-Based Image Analysis to Track Vehicles

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Prabakaran, P. Jayasudha, R. Sandhu, Mukta Gupta, Sandeep School of Computing Sciences Vels Institute of Science Technology and Advanced Studies Department of Computer Applications Chennai India Dr.N.G.P.Institute of Technology Department of Mathematics Coimbatore India Shri Vishwakarma Skill University Skill Department of Computer Science and Engineering Haryana Palwal India Department of Electrical Engineering Dehradun India

ISBN: (纸本)9798350371055

There are many ways to track the traffic conditions on roads. With the rise of AI-based image processing technology, there has been a surge in interest in developing traffic monitoring systems that rely on camera vision data. An improved road monitoring system may be derived from the data collected in this research by placing a camera at a junction. The technique detects and classifies vehicles using a deep-learning-based methodology (YOLOv4). By comparing the positions of the vehicle with the map HD, lane-by-lane trajectories of the vehicle may be approximated. The predicted vehicle trajectories are used to calculate each lane's wait lengths and traffic volumes, broken down by travel direction. This technique was evaluated using five distinct metrics: vehicle detection rates, trajectory prediction, type of vehicle categorization, traffic volume estimate, and queue length assessment. Thousands of samples were used to assess its performance. Based on the findings, it is acceptable to assume that the system can identify vehicles with a 98% success rate and an error rate of less than 25% regarding lane-by-lane trip volume estimation and vehicle type classification. Therefore, this study's approach reveals the viability of collecting comprehensive traffic information from a camera set up at a junction. Current traffic monitoring schemes have a reasonable likelihood of being developed by this study's significant contribution, which is a strategy that combines AI with HD map approaches. © 2024 IEEE.

关键词： Artificial Intelligence HD Map Traffic Monitoring System Vehicle Type Classification YOLOv4

来源：评论

学校读者我要写书评

暂无评论

Quantum Machine Learning Techniques based on Nurturing Agri-Ontology Framework in Agricultural Science 3

Quantum Machine Learning Techniques based on Nurturing Agri-...

引用

3rd International Conference on Applied Artificial Intelligence and computing, ICAAIC 2024

作者： Deepa, R. Jayalakshmi, V. Thilakavathy, P. Bennet Prabhu, A. Surendran, R. Srm Institute of Science and Technology School of Computing Department of Computing Technologies Chennai India Drbccc Hindu College Department of Computer Applications Chennai India Computer Science and Engineering Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India Kone Elevator India Technology & Engineering Centre Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350375190

The absence of a consistent ontological framework often impedes efficient knowledge organization and sharing within the agricultural community, despite the quantity of data created in agricultural research. The lack of defined vocabulary and conceptual frameworks hinders data integration, agricultural research, and innovation by preventing interoperability between databases and systems. To address these issues, this research work proposes the Nurturing Agri-Ontology Framework (NAOF), which offers a systematic approach to creating and updating agricultural ontologies. Ontologies that faithfully portray agricultural ideas and connections can be more easily created with the help of NAOF, which combines ideas from knowledge management, agricultural science, and ontology engineering. NAOF aims to ensure that the ontologies produced reflect the wide range of viewpoints and terminology used in agricultural research by encouraging cooperation among stakeholders, ontology engineers, and domain specialists. In this study, the improvement of knowledge organization, sharing and integration in the agricultural area is shown with the application of NAOF. Using this research study, scientists can build ontologies that improve agricultural decision-making, data interoperability, and the discovery of new information. Using quantum machine learning techniques, a strong foundation of knowledge can be laid for several agricultural applications, such as precision agriculture, crop management, and the formulation of agricultural policies. Ontology coverage, interoperability, scalability, and usability are established evaluation parameters that are used to assess the efficacy of NAOF in this research work. The analysis shows that NAOF effectively solves the problems and creates a better agricultural knowledge ecosystem by thoroughly evaluating it using these standards. © 2024 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Enhancing Stock Price Prediction Through Integration of Astrological and Astronomical Data using XGBoost

引用

Procedia Computer Science 2025年 258卷 3970-3979页

作者： Rekha R Nair Tina Babu Kishore S Vishal S Sheila Mahapatra Department of Computer Science and Engineering Alliance School of Advanced Computing Alliance University Bengaluru India Department of Computer Applications Nitte Deemed to be university Nitte Institute of Professional Education Mangalore Karnataka India Department of Computer Applications School of Engineering Dayananda Sagar University Bengaluru India Department of Electrical and Electronics Engineering Alliance University Bangalore India

Predicting stock prices continues to be a significant challenge in the financial industry, prompting researchers to investigate various methods to improve accuracy. Hence proposed a novel approach by incorporating astrological and astronomical data into XGBoost models for stock price classification and prediction, utilizing deep neural networks (DNN). The dataset is collected from NASA JPL Horizons and Jaganath Hora software. The raw data is preprocessed with feature engineering, data cleaning, []and normalization to obtain a better forecasting stock prices and classification results. The proposed data executed with machine learning models, such as logistic regression, decision trees, random forest, SVM, XGB Classifier, LSTM, RNN, and CNN other than XGB Regressor for the forcasting. The proposed research is evaluated for classification with accuracy, precision, recall, F1 score, and forecasting with RMSE, MAE, R 2 , AIC, and BIC. The XGBoost classifier achieved 99% accuracy in predicting stock market movements, surpassing other models in determining whether the next day’s stock price would be higher or lower than the previous day’s price, while the DNN performed the best among all algorithms for overall stock price prediction. This approach could influence investment strategies, potentially affecting wealth distribution and financial market stability.

关键词： Independent Component Analysis Principal Component Analysis Probable Neural Network Expectation Maximization algorithm Natural language processing

来源：评论

学校读者我要写书评

暂无评论

AXIM: A Programmable Simulation Environment for FPGA Kernels with AXI Interfaces

AXIM: A Programmable Simulation Environment for FPGA Kernels...

引用

IEEE Information Technology and Mechatronics Engineering Conference (ITOEC)

作者： Long Lin Cuncun Shi He Yang State Grid Laboratory of Grid Advanced Computing and Applications State Grid Smart Grid Research Institute co. Ltd Beijing China

In the recent decade, the development of FPGA kernels raises its level of abstraction from RTL to HLS C or OpenCL. And so are the simulation and debugging software suites. However, it makes some existing high-quality RTL simulators incompatible to use. Therefore, we propose AXIM, a programmable simulation environment that integrates existing RTL simulators for FPGA kernels with interfaces at a high-level abstraction via AXI buses. AXIM consists three modules, including AXIM hardware driver, AXIM runtime library, and AXIM debugger. Experimental results show that AXIM runs faster than the one integrated with Xilinx Vitis. Besides, another experiment demonstrates that visualization analysis of DRAM's activities generated by AXIM can help developers optimize the design of kernels. As a side product, we also identify an inconsistent behavior in hardware emulation in Xilinx Vitis 2019.2 about data transfer using AXI interfaces.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Method for Defects Inspection of Power Transmission Lines Based on DETA and Integrated Improvement Algorithm

A Method for Defects Inspection of Power Transmission Lines ...

引用

IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC)

作者： Jin Wang Bo Wang Peng Wu Guoliang Zhang Jiangqi Chen Xi Zhang State Grid Laboratory of Grid Advanced Computing and Applications State Grid Smart Grid Research Institute Co.Ltd Beijing China

Collecting images through drone and helicopter aerial photography is one of the main methods for transmission line inspection. Currently, the popular intelligent transmission defects recognition is mainly based on deep neural network object detection algorithms. Due to the outstanding performance in various public datasets and rapid development of DETR algorithms, there is a promising application prospect in the field of transmission inspection. This article proposes a transmission line inspection model based on DETA, which is optimized by integrated improvement algorithm, which inlcudes SNIP sampling algorithm, multi-scale inference strategy, and prior knowledge based box-selection algorithm. Experiments have shown that the method proposed in this article has the advantages of accurate defect localization, high detection accuracy, and strong scalability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online Fine-tuning Method for Power Grid Artificial Intelligence Model Based on Cloud-Edge Collaboration

Online Fine-tuning Method for Power Grid Artificial Intellig...

引用

Robotics, Automation and Intelligent Control (ICRAIC), International Conference on

作者： Zexu Du Guoliang Zhang Yi Zhang Wei Wei Zongbo Chu State Grid Laboratory of Grid Advanced Computing and Applications State Grid Smart Grid Research Institute Co.ltd Beijing China

As artificial intelligence methods play an increasingly important role in the digital transformation of power grids, when applied in power grid scenarios, these methods face problems such as the inability of models to adaptively deploy data distribution changes, slow response speed, inability to ensure data security on the side, limited computing power on the side, and uneven distribution of computing resources. This method proposes a novel fine-tuning framework based on cloud-edge collaboration to address these issues. This method utilizes reinforcement learning to segment the model, discarding unreliable samples collected on-site to fine-tune the model’s fine-tuning parameters. Finally, validation was conducted on the application scenario of detecting violations in the power grid, and the experimental results show the effectiveness of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NodeMCU-based Smart Car Parking System for Real-Time Monitoring and Efficient Space Utilization

NodeMCU-based Smart Car Parking System for Real-Time Monitor...

引用

IT Innovation and Knowledge Discovery (ITIKD), International Conference on

作者： Rekha R Nair S Kishore Tina Babu Department of Computer Science and Engineering Alliance School of Advanced Computing Alliance University Bengaluru India Department of Computer Applications Nitte Institute of Professional Education Nitte (Deemed to be University Mangalore India

ISBN: (数字)9798350355468

ISBN: (纸本)9798350355475

The rapid increase in vehicle ownership has created a pressing demand for larger parking areas and efficient parking management solutions. This study proposes an innovative NodeMCU-based smart car parking system to address the challenges of efficient parking space management i n urban areas. The system utilizes NodeMCU technology, built on the ESP8266 micro-controller, to provide real-time monitoring and optimize parking space utilization. The architecture incorporates NodeMCU devices equipped with sensors to detect vehicle presence in individual parking spots, wirelessly transmitting data to a central server for processing and analysis. The server implements robust data processing and storage mechanisms, along with a user-friendly interface for easy retrieval of parking information. This approach aids in efficient parking space management and helps reduce illegal parking incidents. By providing real-time data and easy-to-use interfaces, the system helps drivers quickly locate available spots, potentially decreasing traffic congestion and parking-related frustration. The proposed smart parking solution aims to streamline parking management, improve urban mobility, and Improve the entire parking experience for drivers in increasingly crowded metropolitan locations. This research contributes to the development of smart city infrastructure, offering a practical solution to modern parking challenges.

关键词： Technological innovation Smart cities Transfer learning Pressing Automated parking Real-time systems Servers Traffic congestion Vehicles Residual neural networks

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：