检索结果-内蒙古大学图书馆

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

作者： Divya, S.B. Mary, S. Prince Department of Computer Science and Engineering Sathyabhama Institute of Science & Technology Chennai India Mangalam College of Engineering Department of Computer Applications India

ISBN: (纸本)9798350372816

The broad utilization of interconnectivity and interoperability of processing frameworks have turned into an irreplaceable need to improve our everyday activities. All the while, it opens a way to exploitable weaknesses that work out positively past human control capacity. The weaknesses consider network protection instruments fundamental to accepting correspondence trade. Secure correspondence requires safety efforts to battle the dangers and necessities headways to safety efforts that counter advancing security dangers. So, emerging technologies like Deep Learning/ Machine Learning (DL/ML) come in handy for integration and better prediction. So, in this paper, we depict various deep learning/ML strategies used in detecting the imbalance in network traffic. The document also includes research that has been proposed on the topic of intrusion detection in network traffic over the previous four years (2020-2024) by a variety of research specialists. The main achievements of the security measures are recognized in this review together with their quantitative and qualitative success indicators. Additionally, as a guide for upcoming discoveries, this research study examines the major discoveries and the rationale for the lessons discovered. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Exploring Dual-Module Approaches for Sentiment Analysis in Call Recordings 5

Exploring Dual-Module Approaches for Sentiment Analysis in C...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Dhobale, Nikita Dinkar Elle, Krisha Ramesh Deshmukh, Pratiksha Vilas Nirne, Sakshi Sidram Jarali, Prof. Ashwini International Institute of Information Technology Department of Computer Engineering Pune India

ISBN: (纸本)9798350379945

The system entails the development of a sentiment analysis system consisting of two integral modules aimed at analysing audio recordings of calls. The first module predicts sentiment-positive, negative, or neutral-by converting speech to text using speech-to-text APIs and subsequently applying machine learning algorithms including Random Forest, Naive Bayes, SVM, and Logistic Regression. The second module employs audio processing techniques utilising Librosa for feature extraction and Convolutional Neural Networks (CNNs) for emotion recognition. The system facilitates comparisons between the results obtained from both modules for call recordings. Users, starting with system administrators, can choose between two options: browsing for uploading pre-recorded audio files or live recording. In both scenarios, the system executes sentiment analysis and emotion detection, presenting results derived from speech-to-text and audio processing analyses. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Cricket Team Selection and Player Analysis using Data Analytics 6

Cricket Team Selection and Player Analysis using Data Analyt...

引用

6th IEEE International Conference on Recent Advances in Intelligent Computational Systems, RAICS 2024

作者： Raajesh, Sanjay Martin, Noel Jiji, Jyothsna Nair, Aakash Haritha, H. Muthoot Institute of Technology and Science Department of Computer Science and Engineering India

ISBN: (纸本)9798350381689

The inception of the 'Cricket Team Selection and Player Analysis using Data Analytics' project arose from the imperative to introduce precision through data-driven methods in the process of selecting cricket teams. Recognizing the pivotal role of team composition in the sport, our project employs the K-means clustering algorithm to categorize players based on their historical performance data with the strike rate. This approach facilitates the streamlined creation of well-balanced teams, targeting cricket enthusiasts, coaches, and team selectors. The ultimate goal is to enhance their decision-making processes, optimizing team performance and strategy. The project adopts a comprehensive approach, heralding a new era in cricket by leveraging data. It enables the formation of playing elevens derived from historical player performance metrics, ensuring a more resilient and strategic selection process. The project also has a selection of top players based on the attributes provided by the user. The tangible outcome of this project is a tool designed to serve cricket stakeholders, aiding them in making informed decisions for improved performance on the field. Representing a significant stride towards a more data-driven approach to cricket, the 'Cricket Team Selection and Player Analysis using Data Analytics' project is poised to redefine team selection and strategy in the sport. Its applicability extends to a broad audience, promising to be a transformative force in the realm of cricket decision-making. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Development of a Naive Bayes-based Framework for Optimizing Crop Recommendation System and Enhancing Agricultural Yield Prediction 4

Development of a Naive Bayes-based Framework for Optimizing ...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Swetha, P. Senthilkumar, J. Kalaignar Karunanidhi Institute of Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798331523923

This research study proposes a comprehensive Crop Recommendation System that uses advanced machine learning to boost agricultural productivity. By analyzing key environmental and soil factors, including soil composition, pH, temperature, humidity, and rainfall, the system offers customized, data-driven crop suggestions to optimize yield and promote sustainable farming. The system evaluates several algorithms, including Naive Bayes, Decision Tree, Logistic Regression, and Random Forest, and identifies Naive Bayes as the top performer for accurately predicting crop suitability. This multi-algorithm approach represents a significant advancement in precision agriculture, empowering farmers and policymakers with actionable insights to drive improvements in the agricultural sector. Leveraging historical data, the Crop Recommendation System supports farmers, consultants, and policymakers in making more informed and strategic crop selection decisions. The system's precision and adaptability make it a valuable resource for stakeholders focused on improving resource efficiency and fostering sustainable agriculture, ultimately enhancing food security and minimizing environmental impact. © 2025 IEEE.

关键词： Agriculture Crop Recommendation System Decision Tree Logistic Regression Machine Learning Naive Bayes Random Forest

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Recognition Using Mel-Frequency Cepstral Coefficients & Convolutional Neural Networks 2

Speech Emotion Recognition Using Mel-Frequency Cepstral Coef...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Kadam, Shubhan Jani, Jay Kudtarkar, Aniket Koshy, Reeta Sardar Patel Institute of Technology Department of Computer Engineering Mumbai India

ISBN: (纸本)9798350327533

Speech emotion recognition (SER) plays a key role in human-computer interaction, affective computing, mental health diagnosis, and natural language processing (NLP). This paper presents a groundbreaking approach to SER utilizing Mel-Frequency Cepstral Coefficients (MFCC) for feature extraction and a hybrid architecture combining Convolutional Neural Networks (CNN) and transformers. While early methods relied on handcrafted features and traditional machine learning algorithms, recent advancements introduced recurrent neural networks (RNNs). However, limitations in capturing long-term dependencies prompted the exploration of alternative architectures. The proposed method integrates CNNs to capture spectral features and transformers to model long -range dependencies, mitigating existing shortcomings. Evaluation on a publicly available dataset showcases improved accuracy and reduced computational complexity. Comparative analysis against conventional RNN-based models validates the efficacy of the hybrid architecture. The study significantly enhances SER systems, enabling precise emotion analysis in diverse NLP applications. Utilizing CNN for spatial feature representation and the Transformer for sequence encoding, an 80.44% accuracy is achieved on a held-out test set derived from the RAVDESS dataset. This hybrid approach is capable of capturing both local and global speech features, holds promise for real-time emotion prediction in applications like speech therapy, human-robot interaction, and customer service sentiment analysis. © 2024 IEEE.

关键词： Convolutional Neural Networks (CNN) Deep Learning Human-computer Interaction Mel-frequency Cepstral Coefficients (MFCC) Natural Language Processing Speech Emotion Recognition Transformers

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Effort Estimation Models for Software Development Projects related Datasets with diverse features 2

Machine Learning based Effort Estimation Models for Software...

引用

2nd International Conference on Computational Intelligence, Communication technology and Networking, CICTN 2025

作者： Thakur, Vaishali Dutta, Kamlesh Computer Science & Engineering Department National Institute of Technology HP Hamirpur India

ISBN: (纸本)9798331530389

This research evaluates the performance of machine learning models for the estimation of software effort using diverse datasets with distinct feature sets and varying training-test splits. To address the risks of under or overestimation in project management, the study employs robust data preprocessing, feature engineering, and selection techniques. Through extensive experimentation, the study analyzes model accuracy using multiple metrics such as Mean Absolute Error, R-squared, precision, recall, Fl-score, and Receiver Operating Characteristic Area Under the Curve. Preprocessing techniques, including feature scaling and outlier removal, were applied to reduce overfitting and improve generalization. Performance was assessed using various indicators, with results showing that the stacked ensemble model consistently outperformed other models like Linear Regression, Support Vector Regression, and Gradient Boosting in generating accurate predictions across datasets. The analysis revealed that no single data split yielded optimal performance for all datasets;instead, different datasets performed best under customized splits. Larger datasets performed well with splits like 70-30, while smaller ones exhibited overfitting even after preprocessing. Models like Random Forest, XGBoost, and Gradient Boosting demonstrated robust performance, especially on larger datasets, while smaller datasets highlighted challenges with models like K-Nearest Neighbors and Naive Bayes due to overfitting and poor generalization. These findings underscore the importance of adapting data-splitting strategies to the characteristics of individual datasets, offering a pathway to improve estimation accuracy in diverse software development scenarios. The research highlights that larger datasets enable better generalization, while smaller datasets require careful model and preprocessing choices to mitigate overfitting and achieve reliable results. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Retinal Disease Detection for Low Resource Devices Through Pruned and Quantized CNNs

Retinal Disease Detection for Low Resource Devices Through P...

引用

2025 IEEE International Students' Conference on Electrical, Electronics and computer Science, SCEECS 2025

作者： Gavel, Harish Azad, Chandrashekhar National Institute of Technology Jamshedpur Department of Computer Science and Engineering Jamshedpur India

ISBN: (纸本)9798331529833

Retinal disease diagnosis is one of the crucial step for preventing vision loss, especially in conditions such as Diabetic Retinopathy(DR), Glaucoma, and Age-related Macular Degeneration(AMD). In this paper, we propose an efficient approach for retinal disease classification using lightweight convolutional neural networks (CNNs) deployed on a low-resource device, the Raspberry Pi 4. To address the limitations of resource-constrained hardware, we employ model optimization techniques, including pruning and quantization, to reduce computational requirements while maintaining classification accuracy. The proposed system is evaluated on the Messidor datasets. Our optimized MobileNet and EfficientNetLite models decreased the accuracy scores by 1.5% to 2%, while reducing inference time by over 50% and memory usage by 45%. These results show the feasibility of deploying real-time retinal disease models on edge devices for telemedicine and mobile health in resource-limited settings. © 2025 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

THE EFFICIENCY AND SECURITY OF MULTI-UNMANNED AERIAL VEHICLE COMMUNICATION NETWORKS: FEDERATED LEARNING BASED ON LIGHTWEIGHT BLOCKCHAIN

引用

International Journal of Electrical engineering 2024年第1期31卷 23-31页

作者： Chung, Hao-Tse Wang, Li-Chun Cheng, Shao-Hung Institute of Electrical and Computer Engineering National Yang Ming Chiao Tung University Taiwan Department of Electrical and Electronic Engineering Chung Cheng Institute of Technology NDU Taiwan

This study develops an innovative federated learning framework specifically designed for multi-unmanned aerial vehicles (UAVs), utilizing blockchain technology to achieve lightweight, secure, and efficient data processing. In this architecture, UAVs directly participate in federated learning without the need for a central server. Instead, a series of base stations execute blockchain nodes to process gradient information and maintain the system. We eliminate single points of failure by transferring gradient aggregation from the central server to blockchain nodes, thereby enhancing the system’s stability and reliability. Furthermore, the use of a private Inter Planetary File System (IPFS) reduces storage and communication costs. A Byzantine Fault Tolerance (BFT) consensus mechanism is adopted to improve system efficiency and security. Experiments confirm that our proposed architecture effectively prevents model poisoning attacks, even in scenarios where malicious blockchain nodes are in the majority, thus ensuring learning performance. Finally, a node reputation selection mechanism based on the Multi-Krum algorithm is introduced to increase the likelihood of nodes submitting high-quality gradients, thereby enhancing overall system efficiency. © 2024, Chinese institute of Electrical engineering. All rights reserved.

关键词： Aircraft communication

来源：评论

学校读者我要写书评

暂无评论

StressSense: An IoT-Enabled Platform for Stress Level Prediction, Prevention, and Methods There of 6th

StressSense: An IoT-Enabled Platform for Stress Level Predic...

引用

6th International Conference on Recent Innovations in Computing, ICRIC 2023

作者： Gandhala, Santhosh Phanitalpak Joshi, Shubham Das, Sonali Saha, Upasana Department of Computer Science and Engineering Symbiosis Institute of Technology Pune India

ISBN: (纸本)9789819778614

As eloquently articulated by the esteemed sociologist and writer Chelsea Erieau, stress is a dynamic force, akin to an accelerator that exerts its influence, invariably driving individuals either forward or backward. This proposed project emerges as a beacon of hope, offering a sophisticated and highly effective solution for the detection and management of stress levels. It harnesses the power of cutting-edge physiological sensors, encompassing a pulse sensor (MAX30102), a Galvanic Skin Response sensor (GSR Grove v2.0), a body temperature sensor (DS18B20), and an array of other essential data sources like the smart watches (Apple Watch Ultra and Noise BT) for vitals. In conjunction with this, it introduces a user-centric application interface that has been meticulously crafted for the real-time analysis of sensor data, representing a revolutionary step forward in stress management. This interface leverages the prowess of advanced machine learning (ML) libraries and techniques, including TensorFlow and PyTorch for deep learning, regression models, and Scikit-learn for ensemble learning, as well as kNN models. It provides a dynamic and robust platform to monitor physiological responses and offer personalized recommendations. This user-centric approach empowers individuals to navigate the challenges of stress and achieve well-being. This innovative solution marks a significant shift toward personalized stress management, offering a lifeline to individuals seeking to mitigate the negative impacts of stress and lead a healthier, balanced life. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Physiological models

来源：评论

学校读者我要写书评

暂无评论

Sentiment Polarity Analysis of Bangla Food Reviews Using Machine and Deep Learning Algorithms 3

Sentiment Polarity Analysis of Bangla Food Reviews Using Mac...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Amin, Al Sarkar, Anik Islam, Md Mahamodul Miazee, Asif Ahammad Islam, Md Robiul Hoque, Md Mahmudul Uttara University Department of Computer Science and Engineering Dhaka Bangladesh National Institute of Technology Silchar India University of Oslo Department of Informatics Oslo Norway Maharishi International University Department of Computer Science Iowa United States CCN University of Science & Technology Department of Computer Science and Engineering Comilla Bangladesh

ISBN: (纸本)9798350388282

The Internet has become an essential tool for people in the modern world. Humans, like all living organisms, have essential requirements for survival. These include access to atmospheric oxygen, potable water, protective shelter, and sustenance. The constant flux of the world is making our existence less complicated. A significant portion of the population utilizes online food ordering services to have meals delivered to their residences. Although there are numerous methods for ordering food, customers sometimes experience disappointment with the food they receive. Our endeavor was to establish a model that could determine if food is of good or poor quality. We compiled an extensive dataset of over 1484 online reviews from prominent food ordering platforms, including Food Panda and HungryNaki. Leveraging the collected data, a rigorous assessment of various deep learning and machine learning techniques was performed to determine the most accurate approach for predicting food quality. Out of all the algorithms evaluated, logistic regression emerged as the most accurate, achieving an impressive 90.91% accuracy. The review offers valuable insights that will guide the user in deciding whether or not to order the food. © 2024 IEEE.

关键词： Sentiment analysis

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：