检索结果-内蒙古大学图书馆

2024 International Conference on Emerging Innovations and Advanced Computing, INNOCOMP 2024

作者： Guru Prasad, M.S. Praveen Gujjar, J. Kotiyal, Arnav Prasanna Kumar, H.R. Devadas, Raghavendra M Jahan, Afsar Department of Computer Science and Engg. Dehradun India Faculty of Management Studies Bengaluru India Visvesvaraya Technological University PESITM Dept. of Information Science & Engg. Shivamogga India Gitam School of Technology Department of Computer Science and Engineering Gitam University Bengaluru India Department of Computer Application Dehradun India

ISBN: (纸本)9798350376470

As the field of machine learning continues to advance, the importance of effective exploratory data analysis (EDA) cannot be overstated, especially in the context of classification problems. This research paper introduces an innovative and automated approach to exploratory data analysis using Autoviz, a powerful Python library designed to streamline the visualization process for machine learning datasets. The study aims to demonstrate the efficacy of Autoviz in meaningful insights, facilitating feature understanding, and supporting data preprocessing for classification tasks. Furthermore, the paper discusses how Autoviz assists in feature selection by highlighting the relevance and importance of each feature about the target variable. This feature-centric analysis contributes to optimizing machine learning models by guiding the selection of relevant input features, thereby improving model accuracy and interpretability. Autoviz is a Python library designed to automate the exploratory data analysis (EDA) process for machine learning tasks. It is specifically tailored to generate a variety of visualizations that aid in understanding the structure and characteristics of a dataset. The results indicate that Autoviz significantly reduces the time and effort required for exploratory data analysis while maintaining the quality and depth of insights obtained. The differences between Autoviz and Pycaret is discussed in this paper. It has been observed that AutoViz automates the process of exploring and analyzing data, while PyCaret is designed for the comparison, construction, and tuning of machine learning models. © 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

Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction 38

Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary r...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Luo, Haoran Haihong, E. Yang, Yuhao Yao, Tianyu Guo, Yikai Tang, Zichen Zhang, Wentai Peng, Shiyao Wan, Kaiyang Song, Meina Lin, Wei Zhu, Yifan Tuan, Luu Anh School of Computer Science Beijing University of Posts and Telecommunications China School of Automation Science and Electrical Engineering Beihang University China Beijing Institute of Computer Technology and Application China Inspur Group Co. Ltd. China College of Computing and Data Science Nanyang Technological University Singapore

Beyond traditional binary relational facts, n-ary relational knowledge graphs (NKGs) are comprised of n-ary relational facts containing more than two entities, which are closer to real-world facts with broader applications. However, the construction of NKGs remains at a coarse-grained level, which is always in a single schema, ignoring the order and variable arity of entities. To address these restrictions, we propose Text2NKG, a novel fine-grained n-ary relation extraction framework for n-ary relational knowledge graph construction. We introduce a span-tuple classification approach with hetero-ordered merging and output merging to accomplish fine-grained n-ary relation extraction in different arity. Furthermore, Text2NKG supports four typical NKG schemas: hyper-relational schema, event-based schema, role-based schema, and hypergraph-based schema, with high flexibility and practicality. The experimental results demonstrate that Text2NKG achieves state-of-the-art performance in F1 scores on the fine-grained n-ary relation extraction benchmark. Our code and datasets are publicly available. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pruning Optimization of Deep Learning Model Based on Generalization Estimation

Pruning Optimization of Deep Learning Model Based on General...

引用

Artificial Intelligence, Deep Learning and Neural Networks (AIDLNN), International Conference on

作者： Xuanzhe Li Wenjun Ke Wantao Wen Shaotong Liu Xiaojuan Sheng School of Computer Science and Engineering Southeast University Beijing Institute of Computer Technology and Application

ISBN: (数字)9798331520816

ISBN: (纸本)9798331520823

Existing research has shown that deep learning models contain considerable redundancy, requiring compression optimization to eliminate unnecessary parameters and improve computational efficiency. In model compression through pruning, many existing methods often use loss values to guide the identification of sub-network models. However, low training loss does not necessarily indicate good generalization ability. Consequently, reducing model parameters while preserving strong generalization performance has become a key area of research. Addressing the challenge of ensuring strong generalization performance of submodels after optimization through deep learning model pruning, we propose a channel-structured generalization estimation model. The model architecture incorporates Fully Connected Neural Networks (FCNN) and Gated Recurrent Units (GRU) as modules for channel feature extraction. Additionally, we introduce a differentiable pruning algorithm based on generalization estimation. Experimental results demonstrate the capability of the channel-structured generalization estimation model in predicting the generalization gap via regression. Furthermore, the proposed differentiable pruning algorithm effectively safeguards the generalization capability of sub-models. We conduct pruning experiments on NiN-structured convolutional neural network models on two datasets, CIFAR-10 and SVHN. Comparative experimental results demonstrate the effectiveness of this approach: achieving a 0.72% accuracy improvement over the original model on CIFAR-10; and a 0.12% accuracy improvement over the base model on SVHN while reducing FLOPs by 50.2%, validating the effectiveness of the proposed approach.

关键词： Deep learning Training Accuracy Computational modeling Neural networks Estimation Logic gates Prediction algorithms Convolutional neural networks Optimization

来源：评论

学校读者我要写书评

暂无评论

Extrapolative Preservation Management of Medical Equipment through IoT 1

Extrapolative Preservation Management of Medical Equipment t...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Tripathi, Rajeev Mishra, Vinay Kumar Maheshwari, Himani Tiwari, Raj Gaurang Agarwal, Ambuj Kumar Gupta, Ashulekha School of Management Sciences Department of Computer Application and Sciences Lucknow India School of Computer Application Babu Banarasi das University Lucknow India School of Computing Graphic Era Hill University Uttrakhand Dehradun India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India School of Engineering and Technology Sharda University Department of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350330915

The healthcare industry is primarily driven by technological innovations as they are a significant source of inspiration to provide the best patient care. To provide patients with prompt, high-quality care, medical device manufacturing has grown at an unprecedented rate. Hospitals should use the best maintenance techniques to increase the life of their equipment while trying to reduce maintenance costs and efforts as medical device usage increases. This paper proposes a predictive maintenance method (PdM) to assist in identifying critical equipment failures with diverse and frequent failure modes. The proposed method is based on the understanding of the physics of the incident, real-time data collection of relevant parameters using Internet of Things (IoT) technology, and application of machine learning algorithms to predict and classify the condition of the device as good and bad. To demonstrate the feasibility and effectiveness of moving from traditional maintenance to PdM, an economic analysis should be provided. The objective of this study was to determine the challenge of medical device maintenance using an Internet of Things (loT) enabled automated health monitoring system for devices that generate large amounts of data. real-time data, at scale, in healthcare organizations. © 2023 IEEE.

关键词： Failure Management Internet of things IoT Medical Equipment Maintenance Predictive Maintenance Sensors

来源：评论

学校读者我要写书评

暂无评论

Investigating Domain Adaptation for Medical Image Classification 5th

Investigating Domain Adaptation for Medical Image Classifica...

引用

5th International Conference on Data science, Machine Learning and applications, ICDSMLA 2023

作者： Agarwal, Ankita Seth, Jyoti Sharma, Ambrish Kumar Karthikeyan, M.P. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science and Engineering Vivekananda Global University Jaipur India Master of Computer Application Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India

ISBN: (纸本)9789819780426

Area version goals bridge the space between supply and target domain names by remodeling statistics from the source domain to the target area without providing categorized goal facts. Medical image domain version is a critical trouble in scientific imaging obligations, consisting of most cancers prognosis, because it lets in for the switch of understanding throughout particular medical imaging modalities, obligations, and affected person cohorts. It can help address record distribution shifts and make undertaking medical photo classes more dependable and accurate. In this examination, we look into several area model techniques and benchmark their performance in the venture of the medical photo category. We examine supervised and unsupervised methods, as well as deep studying-based methods. The results of our experiments offer insights into the performance of numerous area model techniques for clinical picture class that could assist in deciding the pleasant method to use in any given medical imaging task. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Industrial IoT Smart Manufacturing Systems based on Cloud Computing Energy Efficiency Analysis using Machine Learning Algorithms 3

Industrial IoT Smart Manufacturing Systems based on Cloud Co...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Chinnasamy, P. Khan, Patan Feridoz Sasikala, C. Swathi, Mavalluru Kumar, M. Prema Yadav, Ajay Kumar Kalasalingam Academy of Research and Education School of Computing Department of Computer Science and Engineering Tamilnadu India Mohan Babu University School of Computing Department of Computer Science and Engineering Andhra Pradesh Tirupati India Dept of Cse Andhra Pradesh Ananthapuramu India Audisankara College of Engineering and Technology Andhra Pradesh India Dept. of Ece Andhra Pradesh Bhimavaram India United Institute of Management Department of Computer Application Prayagraj India

ISBN: (纸本)9798331509675

With open connectivity and emergent computing, the Industrial Internet of Things (IIoT) combined with cloud computing resources provides significant breakthroughs in the field of industrial automation. These developments lead to the evolution of supplemental services, which improve automation in the production and industrial sectors. This research proposes novel technique in smart manufacturing system based on cloud computing with IIoT in energy efficiency using machine learning. Here the smart manufacturing process has been analysed based on IIoT with cloud computing network, where the energy efficiency is analysed using virtual machine-based reinforcement markov chain based linear regression. Experimental analysis has been carried out in terms of latency, energy efficiency, task response time, accuracy. proposed technique obtained 97% of Latency, 95% of Energy efficiency, 98% of Accuracy, 94% of Task response time. © 2025 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Understanding and improving fairness in cognitive diagnosis

引用

science China(Information sciences) 2024年第5期67卷 99-114页

作者： Zheng ZHANG Le WU Qi LIU Jiayu LIU Zhenya HUANG Yu YIN Yan ZHUANG Weibo GAO Enhong CHEN Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology& School of Data Science University of Science and Technology of China State Key Laboratory of Cognitive Intelligence School of Computer Science and Information Engineering Hefei University of Technology

Intelligent education is a significant application of artificial intelligence. One of the key research topics in intelligence education is cognitive diagnosis, which aims to gauge the level of proficiency among students on specific knowledge concepts(e.g., Geometry). To the best of our knowledge, most of the existing cognitive models primarily focus on improving diagnostic accuracy while rarely considering fairness issues; for instance, the diagnosis of students may be affected by various sensitive attributes(e.g., region). In this paper,we aim to explore fairness in cognitive diagnosis and answer two questions:(1) Are the results of existing cognitive diagnosis models affected by sensitive attributes?(2) If yes, how can we mitigate the impact of sensitive attributes to ensure fair diagnosis results? To this end, we first empirically reveal that several wellknown cognitive diagnosis methods usually lead to unfair performances, and the trend of unfairness varies among different cognitive diagnosis models. Then, we make a theoretical analysis to explain the reasons behind this phenomenon. To resolve the unfairness problem in existing cognitive diagnosis models, we propose a general fairness-aware cognitive diagnosis framework, FairCD. Our fundamental principle involves eliminating the effect of sensitive attributes on student proficiency. To achieve this, we divide student proficiency in existing cognitive diagnosis models into two components: bias proficiency and fair *** design two orthogonal tasks for each of them to ensure that fairness in proficiency remains independent of sensitive attributes and take it as the final diagnosed result. Extensive experiments on the Program for International Student Assessment(PISA) dataset clearly show the effectiveness of our framework.

关键词： fairness intelligent education cognitive diagnosis psychometrics adversarial learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging AI to Unlock the Potential of Data science 15

Leveraging AI to Unlock the Potential of Data Science

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Yadav, Rakesh Kumar Sudhamsu, Gadug Goyal, Manish Kumar Yuvaraj, S. Deshpande, Leena A. Maharishi University of Information Technology Maharishi School of Engineering and Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Computer Science and Engineering Karnataka Bangalore India Vivekananda Global University Department of Computer Science & Application Jaipur India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India Vishwakarma Institute of Technology Department of Computer Engineering Pune India

ISBN: (纸本)9798350370249

The application of synthetic Intelligence (AI) to records science has spread out a massive array of new possibilities. Via the combination of advanced evaluation strategies, effective understanding-pushed system gaining knowledge of algorithms, and modern computing architectures, AI is allowing researchers to quick and as it should be discover insights from huge and complicated datasets. Furthermore, AI tools are offering corporations with the ability to make higher and more knowledgeable choices from the evaluation of hundreds of thousands of statistics points. The skills of information technology powered by means of AI are revolutionizing industries which includes healthcare, finance, and manufacturing-producing savings, uncovering efficiencies, and identifying new opportunities. As AI-driven records technology maintains to strengthen, organizations that capitalize on its ability stand to gain precious insights and unlock new degrees of overall performance. © 2024 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Energy-Proficient Cluster Enrichment in Wireless Sensor Networks via Categorized Fuzzy Clustering and Multi-Hop Routing Optimization

引用

SN computer science 2025年第1期6卷 1-12页

作者： Shakya, Harish Kumar Chandanan, Amit Kumar Subbalakshmi, Chatti Khambra, Geetanjli Ansari, Mohd Shahnawaz Kushwaha, Ajay Roy, Vandana Artificial Intelligence and Machine Learning Manipal University Jaipur Rajasthan Jaipur India Department of Computer Science and Engineering Guru Ghasidas Vishwavidyalaya (A Central University) Chhattisgarh Bilaspur India Department of Computer Science and Engineerings Guru Nanak Instructions Technical Campus (Autonomous) Ibrahimpatnam Ranga Reddy District Telagana State Hyderabad 501506 India Department of Computer Science and Application The Bhopal School of Social Sciences (BSSS) College M.P. Bhopal India Department of Computer Science and Engineering Eklavya University Damoh MP Damoh India Computer Science and Engineering Rungta College of Engineering and Technology Bhilai India Department of Electronics Communication Gyan Ganga Institute of Technology and Sciences MP Jabalpur India

The WSN's lifetime can be extended by practicing energy saving. By using the appropriate routing mechanism when executing clustering, it can be done successfully. For improved energy conservation, clustering, and routing work together. Clustering lowers duplicate data transmission, while superior routing enables energy-saving travel along the quickest route to the destination. Nodes can be grouped via clustering, and each group will have CH. CH provides data to the BS either directly or via the intermediary nodes. By reducing the workload of resource-limited nodes, clustering chooses CH from resource-rich nodes. The entire network needs to undergo re-clustering in the traditional WSN clustering approach. The suggested protocol creates an energy-efficient cluster head selection approach applying FIS in hierarchical WSNs, which in turn increases sensing network lifetime, power consumption rate, and network communication performance. The proposed FBUCA and Modified minimum spanning tree with fuzzy logic can efficiently route data packets. The load-balancing among clusters and decreased energy usage demonstrated by the proposed model in MATLAB R2016 simulations are key to increasing throughput and extending the network's lifetime. The proposed approach takes into account six of the aforementioned use scenarios. The experimental results confirmed the adaptability and sturdiness of the proposed method, showing that it works well with a large number of WSNs. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： CH FBUCA Fuzzy logic WSN

来源：评论

学校读者我要写书评

暂无评论

Disease Detection in C4 Plants using Machine Learning Approaches 2

Disease Detection in C4 Plants using Machine Learning Approa...

引用

2nd International Conference on Advanced Computing and Communication Technologies, ICACCTech 2024

作者： Singh, Souravdeep Sharma, Geeta Kumar, Ram Kumar, Adesh School of Computer Application Lovely Professional University Punjab Phagwara144411 India School of Computing Science and Engineering VIT Bhopal University Bhopal India School of Agriculture Lovely Professional University Phagwara India

ISBN: (纸本)9798331519056

Disease detection in crops is essential to maintaining food security and agricultural productivity. Plant disease identification is essential to maintaining crop health and increasing agricultural productivity. with the advancement of computational techniques like Machine learning is used for extracting insights from data, enabling automation, and making predictions in various farming domains. Recent assessments reveal that infections that develop on the leaves of plants are causing significant losses for 56% of the agriculture sector. Monitoring the disease's growth and increasing agricultural production is essential. We must first identify the condition early on and take action to stop it from propagating. Therefore, we could potentially able to resolve this challenge by implementing some algorithms for identifying diseases on leaflets. In this study, we investigate the efficacy of Convolutional Neural Networks (CNNs) for detecting diseases in two major crops: maize and sugarcane which lie under C4 plants. Utilizing a dataset located from Kaggle, comprising a diverse range of images depicting various disease symptoms, we trained and evaluated CNN models for both crops. The accuracy of disease detection achieved remarkable results, with 98% accuracy for maize and 100% accuracy for sugarcane. Our comparative analysis highlights the efficacy of CNNs in accurately identifying diseases in these crops, showcasing their potential for aiding farmers in timely disease management and enhancing agricultural yield. © 2024 IEEE.

关键词： C4 Plants Leaf diseases Machine Learning Maize Sugarcane

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：