检索结果-内蒙古大学图书馆

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

A Study on Integrating Machine Learning Techniques for Waste Management 7

A Study on Integrating Machine Learning Techniques for Waste...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Vaidya, Ruchika Dattangire, Rahul Biradar, Divya Verma, Prateek Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India Data Engineering Publicis Sapient HoustonTX77002 United States University of Texas Department of Computer Science ArlingtonTX76019 United States

ISBN: (纸本)9798350372816

The current study focuses on how various Machine Learning (ML) algorithms can be used in waste management and emphasizes the significance of intelligent technologies in addressing contemporary issues. By leading a broad writing survey, the paper features the meaning of incorporating these advances into waste management practices. The system segment subtleties the information assortment, preprocessing, model determination, and assessment measurements utilized in the review. The accuracy and performance metrics of various classifiers, including K Nearest Neighbors, Linear Support Vector Classifier, Logistic Regression, Decision Tree, Multi-Layer Perceptron, and Random Forest, are demonstrated by the results of experiments with them. Especially noteworthy is the MLP classifier's 91.81% accuracy. The discoveries highlight the viability of ML approaches in ssmart waste management. In addition, a comparison table that summarizes the classifiers' accuracy scores provides insight into their suitability for applications in waste management. © 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

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

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

Based on Transfer Learning a Performance Analysis and Comparative Study of CNN for Accurate Plant Disease Detection

Based on Transfer Learning a Performance Analysis and Compar...

引用

2023 IEEE International Conference on Network, Multimedia and Information technology, NMITCON 2023

作者： Nithin, S. Nishanth, M.S. Kodipalli, Ashwini Rao, Trupthi Kumaraswamy, S. Global Academy of Technology Dept of Computer Science and Engineering Banglore India Global Academy of Technology Dept of Artificial Intelligence and Data Science Banglore India Global Academy of Technology Department of Computer Science and Engineering Banglore India

ISBN: (纸本)9798350300826

This paper investigates the use of Convolutional Neural Networks (CNNs) for plant disease diagnosis, utilizing the notion of transfer learning to develop a deep CNN network at a low cost. The dataset utilized includes 30,000 pictures from 18 distinct categories. Several architectural models, including ResNet50, ResNet50V2, VGG16, VGG19, EfficientNetB0, MobileNet, MobileNetV2, NASNetMobile, and DenseNet, were created using transfer learning methodologies. The models are trained on the target plant disease dataset while keeping the features learnt from large-scale image datasets like ImageNet. Performance criteria such as accuracy, precision, and recall are used to assess the models' accuracy in detecting various plant diseasesx. Furthermore, the research investigates the effect of dropout on accuracy and other model parameters in the context of transfer learning. Finally, the outcomes of a tailored model with and without batch normalization are compared. © 2023 IEEE.

关键词： Convolutional 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

Leveraging Instruction-based Learning for Effective UAV Traffic Management in Dynamic Environment

Leveraging Instruction-based Learning for Effective UAV Traf...

引用

2025 International Conference on Multi-Agent Systems for Collaborative intelligence, ICMSCI 2025

作者： Ramya, R.S. Daniel, Keren Lois Rajkumar, S. Madhavan, Sruthi S. Akshya, J. Choudhry, Mani Deepak Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India KGiSL Institute of Technology Department of Computer Science and Business Systems Coimbatore India Sona College of Technology Department of Information Technology Salem India Nehru Institute of Engineering and Technology Department of Artificial Intelligence and Data Science 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)9798331509828

With the popularization of UAVs (Unmanned Aerial Vehicles) in surveillance, delivery services, environmental monitoring, and increasingly other operational aspects, besides the need to take off and land, efficient traffic management becomes integral for assuring and securing further development and exploitation. Most of the existing traffic management systems for UAVs depend on traditional rule-based algorithms or simpler machine learning techniques, such as DQN or PPO. However, these systems also have enormous challenges: dynamic environments, high-density traffic, and robust decision-making over unpredictable weather and network conditions. In addition, the above traditional models usually experience difficulties in balancing exploration and exploitation, leading to suboptimal routing and enlarged collision risks in complicated urban airspaces. These challenges have driven us to develop a new proposal: a UA V traffic management framework based on Double Deep Q-Network (DDQN) combined with Instruction-Based Learning. In this approach, advanced learning for DDQN optimizes processes at decision-making points for UAVs. The model proposed herein, along with comprehensive simulations and quantitative analyses, demonstrated higher performance in terms of leadership and cumulative rewards while keeping lower training loss compared to the classical algorithms such as DQN, A3C, and PPO. At the same time, the DDQN model presented a better success rate (95%), as also reflected in the balanced precision-recall curve showing an area under the curve of 0.90, over others in the on-point prediction of UAVstate and safety margin of collision. Our experimental results demonstrate that the proposed DDQN-based framework significantly enhances UA V traffic management by optimizing energy consumption in complex airspaces and reducing the risk of collision. © 2025 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Security within Security: Attack Detection Model with Defenses Against Attacks Capability for Zero-trust Networks

引用

IEEE Journal on Selected Areas in Communications 2025年第6期43卷 2312-2327页

作者： Wang, Tingting Fang, Kai Cai, Jijing Wang, Lina Tian, Jinyu Feng, Hailin Li, Jianqing Guizani, Mohsen Wang, Wei Macau University of Science and Technology Faculty of Innovation Engineering School of Computer Science and Engineering Macau999078 China Zhejiang A&F University College of Mathematics and Computer Science Hangzhou311300 China Machine Learning Department United Arab Emirates Shenzhen MSU-BIT University Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen518172 China Beijing Institute of Technology School of Medical Technology Beijing100081 China

Traditional traffic anomaly-based attack detection methods in Zero-trust Networks (ZTN) suffer from inherent security vulnerabilities, as they neglect considerations regarding their security defenses. Compromising the attack detection model itself can result in the breakdown of normal attack detection capabilities. Ensuring the security of the attack detection model during runtime presents a novel challenge. To address these shortcomings, we propose a novel attack detection model, termed Security within Security: Attack Detection Model with Defenses Against Attacks Capability for Zero-Trust Networks (SWS), aimed at enhancing the security of ZTN. SWS focuses on achieving attack detection in non-secure detection environments, to maintain its detection capability even when under attack. By employing a soft thresholding method, SWS adapts to the dynamic changes in network traffic, thus reducing the interference of attack signals. The incorporation of an attention mechanism enables SWS to concentrate on analyzing the most indicative traffic features of attack behavior. Additionally, we integrate Residual Networks (ResNet) and Bidirectional Long Short-Term Memory (BiLSTM) to enhance the robustness of identifying complex network attack behaviors. The effectiveness of the SWS is validated through ablation studies, model comparisons, experiments conducted over different training epochs, and experiments conducted on various components of the dataset. Experimental results demonstrate that compared to existing attack detection models, SWS achieves improvements in detection accuracy and recall rate by 13.4% and 10.6%, respectively, while reducing the False Positive Rate (FPR) by 16.9%. © 1983-2012 IEEE.

关键词： Economic and social effects

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

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：