检索结果-内蒙古大学图书馆

Effectiveness and Influence of Parts of Speech like adjectives and interjections for examining the feelings in sentences containing sarcasm: A study 2

Effectiveness and Influence of Parts of Speech like adjectiv...

引用

2nd IEEE International Conference on Advances in Information technology, ICAIT 2024

作者： Adarsh, M.J. Ravikumar, Pushpa Karnataka Chikkamagaluru India Dept. of Computer Science and Engineering Adichunchanagiri Institute of Technology Karnataka Chikkamagaluru India

ISBN: (纸本)9798350383867

In contemporary text analytics, examining the feelings in customer evaluations has taken centre stage. It is difficult to identify emotions in sentences written with irony. Social media portals and e-commerce portals are offering users to come up with comments and reviews with realistic funny emotions. As a way to identify the feelings expressed in sentences written in a mocking tone purpose, we have attempted to highlight the Adjectives function in this study by taking into account positive and negative adjectives as well as an interjection, both good and bad words. We propose the Adjective-based Sarcasm Detection Algorithm (ABSA) and the Interjection-based Sarcasm Detection Algorithm (IBSA) based on lexicon approach as machine learning approaches won't yield better results in detection of irony and have compared it with the existing approach with more sarcastic sentences. Our F score results for ABSA and IBSA are 0.86 and 0.91, respectively. This paper sheds light on investigating humour or irony in context of parts of speech (POS) words. ©2024 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Enhancing Dietary Monitoring using Deep Learning: Food Recognition and Calorie Estimation 15

Enhancing Dietary Monitoring using Deep Learning: Food Recog...

引用

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

作者： Suneela, M. Sahithi, Mandadi Vamsi, Nuthalapati Naik, Nunsavathu Balaji Chowdary, Narra Sujitha Vignan's Lara Institute of Technology & Science College Dept. of Computer Science & Engineering Guntur India

ISBN: (纸本)9798350370249

The project 'Enhancing Dietary Monitoring Using Deep Learning:Food Recognition And Calorie Estimation' introduces an innovative method aimed at improving dietary tracking and fostering healthier eating habits. By employing cutting-edge deep learning techniques, its core objective is to precisely identify various food items and rapidly estimate their caloric content, offering users advanced and personalized monitoring capabilities. Utilizing the Python programming language alongside the MobileNet architecture model, the project underwent rigorous training and evaluation using the expansive Food 101 dataset, comprising 37,046 food images distributed across 101 distinct classes. Notably, the model demonstrated exceptional performance, achieving a training accuracy of 97.02% and a validation accuracy of 98.17%, highlighting the efficacy of this approach in accurately categorizing a wide array of food items. This system provides users with several crucial functionalities. Furthermore, it furnishes users with essential insights by estimating the caloric content of recognized foods, facilitating effective monitoring of dietary intake. The intelligent diet monitoring capabilities enabled by Food Recognition and Calorie Estimation empower users to make informed choices regarding their dietary preferences. Through the continuous tracking and analysis of their daily food consumption, users can glean valuable insights into their nutritional habits, set personalized goals, and make necessary adjustments to achieve a well-balanced and healthy diet. Enhancing Dietary Monitoring Using Deep Learning:Food Recognition And Calorie Estimation stands as a prominent illustration of successful implementation of deep learning techniques, particularly with the utilization of the MobileNet architecture, for food recognition and calorie estimation. With its remarkable accuracy, real-time processing capabilities, and intelligent monitoring features, this project has the potential to revolutioni

关键词： Convolutional Neural Network (CNN) algorithm Datasets MobileNet architecture Web application

来源：评论

学校读者我要写书评

暂无评论

Hybrid Framework for Parking Slot Allocation Using Double Auction and Cooperative Game Theory in Fog-Based Systems 3

Hybrid Framework for Parking Slot Allocation Using Double Au...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Bairi, Pijush Swain, Sujata Bandyopadhyay, Anjan Kalinga Institute of Industrial Technology School of Computer Engineering Bhubaneswar India Haldia Institute of Technology Dept. of Information Technology Haldia India

ISBN: (纸本)9798331523893

The rapid growth of urban transportation necessitates innovative strategies for efficient parking management. Fog-based smart parking systems help reduce latency and improve resource use, but challenges remain in achieving fair and optimal slot allocation. This study presents a hybrid framework that combines a multi-attribute-based double auction mechanism with cooperative game theory. The double auction allocates parking slots fairly, considering both economic and non-price factors like proximity and reputation, while cooperative game theory fosters user coalitions to boost efficiency and satisfaction. By utilizing fog nodes for real-time processing, the system minimizes cloud reliance, ensuring low latency and scalability. Simulations demonstrate significant gains in efficiency, fairness, and responsiveness, showcasing the framework's potential to enhance resource use and promote collaboration for smarter urban mobility. © 2025 IEEE.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

SoulEase : AI Enhanced Personal Journal - Text Based Emotion Detection 7

SoulEase : AI Enhanced Personal Journal - Text Based Emotion...

引用

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

作者： Bodepudi, Naga Reshmi Sabareesh Boddeti, Karthik Reddy Palle, Anshu Bhukya, Lavanya Reddy Bolla, Sai Divya Tej Sreedevi, Ch. B V Raju Institute of Technology Dept. of Computer Science Engineering Medak Telangana Narsapur India

ISBN: (纸本)9798350372816

Self-management is an art of managing your thoughts, feelings and actions that helps you achieve goals in life. In today's expeditious world individual's often struggle to maintain equilibrium between their personal life and work. The proposed web application uses NLP to evaluate the user behavior and mood and prepare a customized routine that balances productivity and rest by dynamically scheduling user's tasks. Current NLP based systems for assessing behavior and mood lack the capacity for thorough and flexible scheduling. It also involves libraries like NLTK. TensorFlow is used which is a machine learning model used to personalize suggestions. The web application analyses journals entered by user using NLP and detect user's emotions. The application gives AI generated prompts for completing their journal. When user enters their daily tasks, this application analyses the previous works of user and plan a daily schedule for them. The application also motivates them to complete their tasks by AI-generated positive affirmations through email. It analyses user's answers of questionnaires designed for stress assessment. This model can take audio, video journaling. The web application integrates with calendar events by using google calendar API. It uses google analytics for mood tracking and analytics. The functionality of the application would be supported by strong frontend and backend architectures that make use of ReactJS for frontend and ***, MySQL, Firebase, for backend. The proposed app can improve sentiment analysis and it is a unique combination of different features and is expected to be 2% higher than any existing models. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing Stockpile Management Through Deep Learning with a Focus on Demand Forecasting and Inventory Optimization

Enhancing Stockpile Management Through Deep Learning with a ...

引用

2024 IEEE International Conference on Recent Advances in Science and engineering technology, ICRASET 2024

作者： Sheela, S. Latha, A.P. Jyothi, S. Vidyarani, H.J. Komala, M. Sharmila, N. Mallikarjunaswamy, S. Pavithra, G.S. Global Academy of Technology Department of Computer Science and Engineering Bengaluru India Dayananda Sagar College of Engineering Department of Information Science and Engineering Bengaluru India Dr. Ambedkar Institute of Technology Department of Information Science and Engineering Bengaluru India Sjb Institute of Technology Dept of Electronics and Communication Engineering Bengaluru India Jss Science and Technology University Dept of Electronics and Electrical Engineering Mysuru India Jss Academy of Technical Eduction Dept of Electronics and Communication Engineering Bengaluru India Rns Insitute of Technology Dept of Computer Science and Alml Bengaluru India

ISBN: (纸本)9798350388602

Stockpile management is essential for industries to efficiently meet customer demands while minimizing costs. Traditional methods like the Economic Order Quantity (EOQ) model and ARIMA often struggle with adaptability and accuracy, leading to inefficiencies such as overstocking or stockouts. This study proposes using Long Short-Term Memory (LSTM) networks to improve demand forecasting in stockpile management. LSTMs are designed to handle sequential data, capturing complex patterns and long-term dependencies that conventional methods miss. The LSTM-based approach achieved up to a 0.30% improvement in forecasting accuracy, resulting in more precise inventory control and better alignment with actual demand. The proposed system, termed Deep Inventory Management (DIM), incorporates LSTM models that adapt to changes in demand by considering factors such as seasonality and trends. This adaptive approach allows for proactive inventory predictions, enhancing decision-making in procurement and stock levels. Key abbreviations include LSTM (Long Short-Term Memory), EOQ (Economic Order Quantity), and DIM (Deep Inventory Management). By aligning inventory more closely with demand, this deep learning approach enhances operational efficiency, reduces costs, and improves customer satisfaction, making it a valuable advancement over traditional inventory management methods. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Recognition of Fes Using A Novel Detection Method Based on Convolutional Neural Networks 1

Recognition of Fes Using A Novel Detection Method Based on C...

引用

1st IEEE International Conference on Innovations in High Speed Communication and Signal Processing, IHCSP 2023

作者： Thakur, Sumit Raza Khan, Nikhat IES UNIVERSITY Department of Computer Science and Engineering Bhopal India IES COLLEGE of TECHNOLOGY Dept. of Computer Science and Engineering Bhopal India

ISBN: (纸本)9798350345957

Currently, the wireless access method utilized by systems is 5G technology. In this study, a lightweight NN for emotion recognition is proposed, where a visual system can be incorporated into devices with a low computational capability to perform face expression classification while simultaneously minimizing the amount of parameters utilized in the classification process. To improve the reliability of the results, it is helpful to package the models as a service that other collaborating systems can use. Face expression resource development frameworks can be tailored to address the requirements of different security models, such as criminal threats, government secrets, etc. This model will have the opposite influence on detection and classification and produces good detection results by identifying photographs inside the dataset, which indicates that the model built into this research is suitable for multi- categorization of facial emotions. In general, comprehended a visual system that can be incorporated on devices with minimal computer capacity to attain result classification and decrease many factors. Following comparison with the algo in recent years, the accuracy of our algo will be higher than theirs, and it has achieved good detection results in photographs inside the dataset after the experimental results. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Forecasting EV Market Trends in India: A Deep Learning Approach for Two/Three-Wheelers 12

Forecasting EV Market Trends in India: A Deep Learning Appro...

引用

12th International Electrical engineering Congress, iEECON 2024

作者： Mishra, Rishav Dev Kumar Dash, Santanu Chudjuarjeen, Saichol Korkua, Suratsavadee School Of Computer Science And Engineering Vellore Institute Of Technology Vellore India Vellore Institute Of Technology TIFAC-CORE Vellore India Rajamangala University Of Technology Krungthep Faculty Of Engineering Dept. Electrical Engineering Bangkok Thailand School Of Engineering And Technology Walailak University Thailand

ISBN: (纸本)9798350383591

This research paper presents a comprehensive analysis of machine learning models for predicting future sales of electric vehicles (EVs) in the Indian Market. With a specific focus on 2 and 3 wheeler sales. The study compares different machine learning approaches, including Linear Regression, Support Vector Regression (SVR), Long Short-Term Memory (LSTM) Neural Network, Through an evaluation of their respective errors, LSTM Neural Network method demonstrates superior prediction accuracy, making it the preferred model for forecasting EV sales, specifically 2 wheeler and 3 wheeler sales over the next five years. The paper aims to present the forecasted sales figures, in hopes of providing valuable insights into the future trajectory of EV sales and serving as a vital resource for stakeholders in the electric vehicle industry. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Challenge-Response Emotion Authentication Algorithm Using Modified Horizontal Deep Learning

引用

Intelligent Automation & Soft Computing 2023年第3期35卷 3659-3675页

作者： Mohamed Ezz Ayman Mohamed Mostafa Ayman Elshenawy College of Computer and Information Sciences Jouf UniversitySakaka72314Saudi Arabia Systems and Computers Engineering DEPT Faculty of EngineeringAl-Azhar UniversityCairo11651Egypt Software Engineering&Information Technology Faculty of Engineering&TechnologyEgyptian Chinese UniversityEgypt

Face authentication is an important biometric authentication method commonly used in security *** is vulnerable to different types of attacks that use authorized users’facial images and videos captured from social media to perform spooﬁng attacks and dynamic movements for penetrating secur-ity *** paper presents an innovative challenge-response emotions authentication model based on the horizontal ensemble *** proposed model provides high accurate face authentication process by challenging the authorized user using a random sequence of emotions to provide a speciﬁc response for every authentication trial with a different sequence of *** proposed model is applied to the KDEF dataset using 10-fold *** improvements are made to the proposed ***,the VGG16 model is applied to the seven common ***,the system usability is enhanced by analyzing and selecting only the four common and easy-to-use ***,the horizontal ensemble technique is applied to enhance the emotion recognition accuracy and minimize the error during authen-tication ***,the Horizontal Ensemble Best N-Losses(HEBNL)is applied using challenge-response emotion to improve the authentication efﬁ-ciency and minimize the computational *** successive improvements implemented on the proposed model led to an improvement in the accuracy from 92.1%to 99.27%.

关键词： Face authentication challenge-response authentication transfer learning and horizontal ensemble technique

来源：评论

学校读者我要写书评

暂无评论

Success Probability Analysis for Joint Sensing and Communications: A Determinantal Point Process Perspective

Success Probability Analysis for Joint Sensing and Communica...

引用

2024 International Conference on Integrated Circuits, Communication, and Computing Systems, ICIC3S 2024

作者： Tharaniya, R. Mukesh, T. Ka, Kameshwari Rajeshkumar, J. Ananthi, G. Thiagarajar College of Engineering Dept of Electronics & Communication Engineering Madurai India R.L.Jalappa Institude Of Technology Dept of Computer & Science Engineering Kodigehalli Karnataka Doddaballapur India

ISBN: (数字)9798350364088

ISBN: (纸本)9798350364088

In this paper, we present a novel framework for analyzing the success probability in Joint Sensing and Communication (JSAC) systems leveraging Determinantal Point Process (DPP). JSAC systems are integral in various applications such as cognitive radio networks and Internet of Things (IoT), where efficient utilization of spectrum resources is paramount. By employing DPP, which models the repulsion among sensing and communication nodes, we offer a rigorous closed form analysis of the success probability in such systems. Proposed the DPP concentrating on repulsive base stations and users, apply the analytically derived empty space function to the signal to interference plus noise ratio equation, and evaluate the results using the quasi-Monte Carlo integration approach in Multiple Input Multiple Output (MIMO) systems. Our framework provides insights into the tradeoffs between sensing performance and communication reliability, aiding in the design and optimization of JSAC networks for enhanced spectrum utilization and system efficiency. Through theoretical analysis and simulation results, we demonstrate the effectiveness of our approach in quantifying the success probability and its implications on system performance, thereby contributing to the advancement of JSAC technologies. © 2024 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Heart Disease Detection Using Machine Learning Models 2

Heart Disease Detection Using Machine Learning Models

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Singh, Amrit Mahapatra, Harisankar Biswal, Anil Kumar Mahapatra, Madhumita Singh, Debabrata Samantaray, Milan Berhampur India Berhampur India Dept. of Computer Science Udayanath Autonomous College of Science and Technology Cuttack India Dept. of Computer Science and Engineering Delhi Technical Campus UP Greater Noida India Bhubaneswar India Department of Computer Science and Engineering Silicon Institute of Technology Bhubaneswar India

An enormous number of deaths occur every year as a result of heart disease, making it a major concern in world health. Improving patient outcomes and lowering death rates, early detection and correct diagnosis of cardiac disease play a key role. When the heart's arteries become blocked, oxygen-poor blood cannot reach the heart properly, resulting in coronary heart disease. Early detection of cardiac disease is viable because it reduces medical costs and potentially saves the patient's life. Recently presented methods have improved heart failure detection accuracy on testing data without sacrificing accuracy on training data, yet most of these algorithms are suffering from the issue of overfitting. Models that were created end up fitting the test data too well. In this study, we create a novel diagnostic system to address this issue, and the resulting system demonstrates high intelligence and excellent performance on both training and testing data. Machine learning (ML) algorithms have demonstrated promising potential in assisting healthcare professionals with timely and accurate diagnosis. In this paper, is based on supervised machine learning methods are decision tree (DT), random forest (RF), Support vector Machine (SVM), Principal Component Analysis(PCA). We compare their accuracy with each other by using bar plot. © 2024 Elsevier B.V.. All rights reserved.

关键词： Blood pressure

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：