检索结果-内蒙古大学图书馆

13th IEEE data Driven Control and Learning Systems Conference, DDCLS 2024

作者： Liu, Guangkun Jin, Huaiping Wang, Bin Yang, Biao Qian, Bin Kunming University of Science and Technology Faculty of Information Engineering and Automation Department of Automation Kunming650500 China Kunming University of Science and Technology Yunnan Key Laboratory of Artificial Intelligence Kunming650500 China

ISBN: (纸本)9798350361674

data-driven soft sensor techniques enable online prediction of key quality variables. However, in real industry, the expensive cost of manual labeling leads to the abundance of unlabeled data and the scarcity of labeled data, which becomes a major obstacle to establishing high-precision data-driven soft sensing. To address this problem, a method based on large-scale pseudo-labeling optimization, LSPLO, is proposed. This method, by introducing confidence assessment, fixes the pseudo labels assessed as high-confidence during optimization, while the low-confidence pseudo labels are used as new decision variables after dimensionality reduction to continue optimization. The original decision variables are reinitialized using superior pseudo labels, and stepwise dimensionality reduction and optimization are performed to obtain the optimal pseudo labels. The superiority of the proposed method LSPLO is demonstrated by a real industrial case of the Chlortetracycline (CTC) fermentation process. © 2024 IEEE.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Demystifying the Role of Big data Analytics in IIoT-Based Connected Railways 3

Demystifying the Role of Big Data Analytics in IIoT-Based Co...

引用

3rd International Conference on Advancement in Electronics and Communication engineering, AECE 2023

作者： Gupta, Navya Narwal, Bhawna Batra, Shivangi Gera, Pooja Bhati, Pooja Department of Artificial Intelligence and Data Science Delhi India Department of Information Technology Delhi India Department of Mechanical and Automation Engineering Delhi India

ISBN: (纸本)9798350330724

Recent advances in sensors, networks, and hardware/software platforms have facilitated the development of Industrial Internet of Things (IIoT) applications in railway transportation. Nevertheless, the limited coverage and battery life of IIoT devices remain significant hurdles in realizing realistic service implementations. Against this backdrop, this study aims to scrutinize the impact of Industry 4.0 and big data analytics on railway engineering, considering factors such as post-COVID requisites and the security and privacy of rail users. Additionally, the research investigates the application of these ideas in India, which presents a challenging environment, and examines potential avenues for future research. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Sign Language to Regional Language Converter 3

Sign Language to Regional Language Converter

引用

3rd International Conference on Smart Technologies, Communication and Robotics, STCR 2023

作者： Mohanrja, S. Babu, C Ganesh Jayendraprabhu, S. Lokeshkumar, V. Trishala, Ag KGiSL Institute of Technology Department of Artificial Intelligence & Data Science Coimbatore India Bannari Amman Institute of Technology Department of Electronics and Instrumentation Engineering Coimbatore India

ISBN: (纸本)9798350370867

In recent days most people who are disabled are not able to make proper communication with others. Deaf people frequently communicate through sign language, a kind of manual communication. There are many different sign languages used by deaf people around the world;sign language is not a global language. Recognizing activities from sign languages is a computer job known as sign language recognition, or SLR for short. The main motive of the project is to translate their sign language to regional language through which we can able to full fil their needs. By providing input data through the form of speech, text, or sign language in the translation process, it is possible to change the translation for them better. © 2023 IEEE.

关键词： Translation (languages)

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition using EEG Signal Classification of seed dataset 2

Emotion Recognition using EEG Signal Classification of seed ...

引用

2nd International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation, ICAECA 2023

作者： Saranya, K. Sudharson, D. Gokila, N.M. Lakshmipriya, S.R. Suriyavathi, K.A.K. Department of Information Science and Engineering Kumaraguru College of Technology Coimbatore India Department of Artificial Intelligence and Data Science Kumaraguru College of Technology Coimbatore India Information Science and Engineering Department Kumaraguru College of Technology Coimbatore India

ISBN: (纸本)9798350306811

Emotions were considered an important component. Everyday lives need emotions on a regular basis. Electroencephalogram (EEG)-based emotion identification was gaining popularity quickly. Signals from electroencephalograms (EEGs) are one of the key resources. The biggest benefit of using EEG signals is that they accurately represent real feelings and it could be prepared by computer systems. EEG is a physiological marker that may be captured from the brain activity within the context of scalp-transmitted brain waves which was used to collect brain signals. With this test, waves representing the brain's activity are recorded. The SEED-IV dataset was utilized to categorize emotions as happy, sad, fear, and neutral. Sampling techniques and classification techniques were used to raise the level of performance of the algorithm. One of the most important advantages of using EEG signals is that is accurately prepared by computer systems and portrayed the real experience. The performance of the emotion recognition systems by brain signals depended on the efficiency of the algorithms used. The instability of the brain's impulses is one of the reasons why this process is seen as challenging. So, pre-process was done to remove noisy data. The proposed method focuses on implementing an algorithm that accurately classified emotions into the said four categories. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Networks for Optimizing Reliability in Vehicle-to-Infrastructure Communication in Autonomous Systems 9

Graph Neural Networks for Optimizing Reliability in Vehicle-...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Neelamegam, G. Revathy, J. Kannukkiniyal, M. Devendran, M. Akshya, J. Choudhry, Mani Deepak Vsb College of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Christ the King Engineering College Department of Artificial Intelligence and Data Science Coimbatore India Kongu Engineering College Department of Computer Science and Engineering Erode India Hindustan institute of technology Department of Computer Science and Engineering Coimbatore India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798350377972

High reliance on autonomous systems necessitates efficient and reliable data exchange through Vehicle-to-Infrastructure (V2I) communication to have appropriate and stable network performance in dynamic vehicular environments. With heuristic approaches, Dijkstra's algorithm, and Deep Q-Networks (DQN), several methods are proposed for optimizing latency reduction, packet delivery rate improvement, and power efficiency in the direction of V2I communications. However, these approaches suffer from important challenges: low adaptability of the network to real-time dynamics, suboptimal resource usage, and difficulties in scalability towards complex large-scale networks. In this scenario, we propose a framework that incorporates a GNN inside autonomous systems for V2I communication to optimize performance. The GNN will process real-time graph features, including signal strength, packet loss, and mobility speed, as it dynamically changes in adaptation to the evolution of network behaviour and other functions. This work shows the superiority of the proposed GNN model for the efficiency of experimentally conducted simulations compared to the current models;it achieved latency reduced by up to 28%, 5-10% PDR, and 20% energy efficiency across the various scenarios with urban, rural, highway, and suburban networks. The results validate robustness and scalability for practical implementations by the proposed approach in real-world autonomous systems. Further development is possible with this framework: for example, the use of multi-agent reinforcement learning techniques within cooperative decision-making and the enhancement through blockchain-based security mechanisms to ensure the integrity of the data. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Crowd Estimation Using Sensors for Public Transport (BUSES)

Crowd Estimation Using Sensors for Public Transport (BUSES)

引用

2023 International Conference on New Frontiers in Communication, Automation, Management and Security, ICCAMS 2023

作者： Sumathi, S. Soms, Nisha Gowtham, S. Pagalavan, M. Hariharan, S. Sri Eshwar College of Engineering Dept. of Artificial Intelligence and Data Science Coimbatore641 202 India Kpr Institute of Engineering and Technology Coimbatore India

ISBN: (纸本)9798350317060

The Population in Indian metropolitan metropolises have been growing at an intimidating rate. In these metropolises, motorcars are generally the most preferred last afar trip, due to their cheap rates and expansive routes. Crowd estimation ways using cameras inside the motorcars aren't suitable. Hence, we've enforced a result using Internet of effects. Crowd operation system is necessary in those circumstances to prevent crowd problems. Therefore, in order to preserve lives, it is very necessary for a frame to be in charge of these masses. In terms of crowd timing and used sweating, this frame shall be clever and efficient. The suggested framework is based on IoT, facilitates relationships between electronic devices, and presents information through smart operations with a tidy, straightforward interface for flexible and simple operation by individuals from all eras. The goal is to support directors' control in an explosive way and distribute to callers over the designated area. The detector, operation, and affiliate layers make up the three layers that make up the frame. The detector subcaste is in charge of gathering crowd data. As a mediator between detectors and affiliate layers, the operation subcaste. It consists of online or other services that are in charge of gathering and analyzing data flowing from the detectors. Additionally, it alerts managers of busy places so they can act appropriately. Later, the appropriate choice will be made and communicated to the interface subcaste. The proposed crowded the machine is and how far is it from their position for which They're staying. To reduce the vexation in the operation of Public Transport System(motorcars) through Integration of tackle and software technologies that provides stoner interface with 1. Live position of the machine (through GPS). 2. Crowd position in the machine (through Detectors). © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Image Identify and Categorization using artificial Neural Networks

Lung Cancer Image Identify and Categorization using Artifici...

引用

2024 International Conference on Computational intelligence for Green and Sustainable Technologies, ICCIGST 2024

作者： Lingappa, Ediga Begum, D Jareena Pachouri, Priya Rashmi, Kuderu Varalakshmi, Thokala Tharuna Kumar, Anoop Mallareddy College of Engineering Maisammaguda Dept of Computer Science and Engineering TS Secunderabad500100 India CMR Institute of Technology Dept. of Artificial Intelligence and Data Science Bengaluru560037 India Malla Reddy University Dept of Cyber Security Hyderabad India

ISBN: (纸本)9798350381887

Lung cancer that is made up of small cells is called small cell lung cancer (SCLC). Smoking tobacco in any form-cigarettes, cigars, or pipes-is by far the most significant risk factor for developing lung cancer, though it is only one of many. Cancer of the lungs is known as lung cancer. When cells in the body multiply uncontrollably, cancer develops. If cancer cells enter the lymphatic system or the bloodstream, they can travel to other organs and spread the disease. Cheap and fast cancer diagnostics could save millions. Latestage cancer treatment is hard. Lung cancer is diagnosed non-invasively. Biopsy requires careful ANN architecture selection. This study proposes a diagnosis ANN model. ANN research is 'hot' in cardiology, cancer, and radiology. Medical research uses ANNs. Lung cancer diagnosis was tested. MR images assess lung health for the neural network. MATLAB created ANNs and processed images. Training data was extracted from MR images using Harlick texture features. MATLAB made ANNs. Elman Network exceeds ANNs with 90.30 %. Lung cancer can develop. MRIs detect lung cancer. MRIs show lung development. Many lung tumour detection research use machine learning and deep learning. MRI algorithms swiftly detect lung malignancies, improving patient therapy. Radiologists use these forecasts. The study evaluates a self-defined ANN for lung tumour identification. The radiologist needs time to find and remove the cancer from the MR. technology improves performance and segmentation. Machines always predict and detect. Neural networks outperformed SVM, Random forest, regression, and others. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Improved optimizer with deep learning model for emotion detection and classification

引用

Mathematical Biosciences and engineering 2024年第7期21卷 6631-6657页

作者： Joseph, Willson C. Kathrine, G. Jaspher Willsie Shanmuganathan, Vimal Sumathi, S. Pelusi, Danilo Valencia, Xiomara Patricia Blanco Verdú, Elena Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Department of Computer Science and Engineering Adi Shankara Institute of Engineering and Technology Kerala India Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore India Sri Eshwar College of Engineering Coimbatore India Communication Sciences University of Teramo Coste Sant’agostino Campus Teramo Italy Universidad Internacional de La Rioja La Rioja Logroño Spain

Facial emotion recognition (FER) is largely utilized to analyze human emotion in order to address the needs of many real-time applications such as computer-human interfaces, emotion detection, forensics, biometrics, and human-robot collaboration. Nonetheless, existing methods are mostly unable to offer correct predictions with a minimum error rate. In this paper, an innovative facial emotion recognition framework, termed extended walrus-based deep learning with Botox feature selection network (EWDL-BFSN), was designed to accurately detect facial emotions. The main goals of the EWDL-BFSN are to identify facial emotions automatically and effectively by choosing the optimal features and adjusting the hyperparameters of the classifier. The gradient wavelet anisotropic filter (GWAF) can be used for image pre-processing in the EWDL-BFSN model. Additionally, SqueezeNet is used to extract significant features. The improved Botox optimization algorithm (IBoA) is then used to choose the best features. Lastly, FER and classification are accomplished through the use of an enhanced optimization-based kernel residual 50 (EK-ResNet50) network. Meanwhile, a nature-inspired metaheuristic, walrus optimization algorithm (WOA) is utilized to pick the hyperparameters of EK-ResNet50 network model. The EWDL-BFSN model was trained and tested with publicly available CK+ and FER-2013 datasets. The Python platform was applied for implementation, and various performance metrics such as accuracy, sensitivity, specificity, and F1-score were analyzed with state-of-the-art methods. The proposed EWDL-BFSN model acquired an overall accuracy of 99.37 and 99.25% for both CK+ and FER-2013 datasets and proved its superiority in predicting facial emotions over state-of-the-art methods. ©2024 the Author(s), licensee AIMS Press.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

DialectMoE: An End-to-End Multi-Dialect Speech Recognition Model with Mixture-of-Experts 23

引用

23rd Chinese National Conference on Computational Linguistics, CCL 2024

作者： Zhou, Jie Gao, Shengxiang Yu, Zhengtao Dong, Ling Wang, Wenjun Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Kunming650500 China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Yunnan Kunming650500 China

ISBN: (纸本)9780000000002

Dialect speech recognition has always been one of the challenges in Automatic Speech Recognition (ASR) systems. While lots of ASR systems perform well in Mandarin, their performance significantly drops when handling dialect speech. This is mainly due to the obvious differences between dialects and Mandarin in pronunciation and the data scarcity of dialect speech. In this paper, we propose DialectMoE, a Chinese multi-dialects speech recognition model based on Mixture-of-Experts (MoE) in a low-resource conditions. Specifically, DialectMoE assigns input sequences to a set of experts using a dynamic routing algorithm, with each expert potentially trained for a specific dialect. Subsequently, the outputs of these experts are combined to derive the final output. Due to the similarities among dialects, distinct experts may offer assistance in recognizing other dialects as well. Experimental results on the datatang dialect public dataset show that, compared with the baseline model, DialectMoE reduces Character Error Rate (CER) for Sichuan, Yunnan, Hubei and Henan dialects by 23.6%, 32.6%, 39.2% and 35.09% respectively. The proposed DialectMoE model demonstrates outstanding performance in multi-dialects speech recognition. © 2024 China National Conference on Computational Linguistics.

关键词： Dynamic routing algorithms

来源：评论

学校读者我要写书评

暂无评论

Twitter Based Complaint Management System for Rail Transit 2

Twitter Based Complaint Management System for Rail Transit

引用

2nd International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation, ICAECA 2023

作者： Saranya, K. Sudharson, D. Aathmika, M. Shakthi, Vel S Shree, Anunitha S Department of Information Science and Engineering Kumaraguru College of Technology Coimbatore India Department of Artificial Intelligence and Data Science Kumaraguru College of Technology Coimbatore India Information Science and Engineering Department Kumaraguru College of Technology Coimbatore India

ISBN: (纸本)9798350306811

People can now more easily express their opinions and ideas to a wider audience through social media platforms such as Twitter, Facebook, and Instagram. Among these social media applications, Twitter has the most trusted users and is one of the most used, with many users tweeting millions of tweets per day. Trusted users, including small and large organizations or companies, respond to customer's tweets that convey their thoughts, like complaints or suggestions, by retweeting them using the microblogging service provided by Twitter. In today's competitive world, Indian Railways manages the second largest railway system by size, which encourages users to communicate to them through tweets on Twitter. This results in a sheer volume of data and makes it impossible for the Railway Administration to answer each user's query or complaint. Sometimes these complaints may include some urgent matters or questions requiring prompt attention. The proposed method focuses on implementing a website where the tweets are classified into different categories based on their temporal nature and are prioritized in cases of emergency. This proposed solution helps the railway administration to easily reply to the tweets and know their quality of service based on the users' feedback. © 2023 IEEE.

关键词： Quality of service

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：