检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Venkata, Manjula Devarakonda Revu, Akhil Kumar Gude, Anisha Pampana, Narendra Palli, Bharath Palepu, Iswarya Devi Dept of Computer Science Pragati Engineering College A.P Kakinada533437 India

Sentiment analysis plays a vital role in deriving opinions and sentiments from text data, for applications from social media tracking to customer feedback analysis and to decision-making systems. While more complex models like Support Vector Machines (SVM) are generally more widely used for sentiment classification, the current work defies the assumption that model complexity is necessarily correlated with better performance. Rather, we demonstrate that with proper preprocessing, a less complex model like Logistic Regression can, in fact, perform better than SVM. Our experimental results, based on a well-pre-processed dataset, show that Logistic Regression achieved accuracy of 0.941, precision of 0.938, recall of 0.938, and F1-score of 0.925 consistently beating SVM. These results demonstrate the paramount need for data preprocessing in sentiment classification, illustrating how an optimized data pipeline can greatly enhance the predictive strength of more primitive models without excessive computational burden. This research emphasizes the need to use the appropriate preprocessing methods to achieve maximum efficiency in sentiment analysis models and thereby make machine learning applications more affordable and accessible. © 2025, The Authors. All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Analysis of Public Sentiment on Dhaka Metro Rail with Transformer Based Architectures 26

Analysis of Public Sentiment on Dhaka Metro Rail with Transf...

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Jeba, Samiha Maisha Taharat Aurpa, Tanjim Siyam, Farshid Hossain Khan, Rajib Mansia, Faniyam Maria International University of Business Agriculture and Technology Dept. of Computer Science and Engineering Bangladesh Bangabandhu Sheikh Mujibur Rahman Digital University Dept. of Educational Technology Bangladesh

ISBN: (纸本)9798350359015

Dhaka Metro Rail is a mesmerizing initiative of the Bangladesh Government that has brought comfort to people. This project got a huge appreciation from people for its continuous service. Mass people use the train for rambling, going to the workplace, etc. Again, for some unwanted circumstances, Dhaka Metro Rail gleaned negative criticism from various *** this research, we analyzed public sentiment on Dhaka Metro Rail from popular social media using recent NLP architectures like BERT, XLNet and Electra, where BERT outperformed than other with an accuracy of 91.11% in correctly identifying the sentiments of the public *** sentiment of a comment is identified into predefined categories, such as positive, negative, or neutral. © 2023 IEEE.

关键词： BERT ELECTRA Metro Rail Sentiment Analysis Vader XLNet

来源：评论

学校读者我要写书评

暂无评论

On Neural-Network-Based Detection for Hypertensive Subjects Using Classification of Retinal Fundus Photographs 53

On Neural-Network-Based Detection for Hypertensive Subjects ...

引用

53rd IEEE International Symposium on Multiple-Valued Logic, ISMVL 2023

作者： Sonetsuji, Yuki Isokawa, Teijiro Kamiura, Naotake Tabuchi, Hitoshi University of Hyogo Graduate School of Engineering Dept. of Electronics and Computer Science Himeji Japan Hiroshima University Dept. of of Technology and Design Thinking for Medicine Hiroshima Japan

ISBN: (纸本)9781665464161

In this paper, a method of detecting hypertensive subjects is proposed, using retinal fundus photographs classified by convolutional neural networks (CNNs for short). The proposed method employs Inception-v3 model as a CNN. The data to be presented to the proposed model are prepared from retinal fundus photographs. The scheme of fine tuning is conducted to construct a discrimination model. The model specifies the photographs corresponding to the subjects being in hypertensive states. Experimental results establish that the proposed method can achieves favorable metric values. Especially, Accuracy value achieved by the proposed method is comparatively high for the small scale of dataset, compared with the previously proposed method. © 2023 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Identification of Fraudulent Transactions for Enhanced Credit Card Fraud Detection 4

Identification of Fraudulent Transactions for Enhanced Credi...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Gupta, Monica Gayathri, V. Narula, Rachna Kumar, Vijay Kaur, Surinder Singh, Neetu Bharati Vidyapeeth's College of Engineering Dept. of Electronics and Communication Engineering New Delhi India Bharati Vidyapeeth's College of Engineering Department of Computer Science and Engineering New Delhi India Bharati Vidyapeeth's College of Engineering Department of Information and Technology New Delhi India

ISBN: (纸本)9798350387490

With the flourishment of the digital era and the evolution of new techniques and technology, this paper highlights the ever-growing risk of credit card fraud. The advancing technology has provided fraudsters with new and untraceable techniques for scamming genuine users. With the increasing impact of fraud, financial institutions must use machine learning tools for scam detection to provide safety and security to their users' accounts. This paper consists of an interdisciplinary comparative analysis of ML algorithms: Random Forest Classifier, XGBoost, ADABoost, Logistic Regression, Decision Trees, and Artificial Neural Networks. The diverse selection of algorithms aims to determine the most effective algorithm with the highest accuracy score for predicting legitimate and fraudulent transactions. The methodology involves fetching data from an Excel file, training the models, testing them on 20% of the dataset, and finally obtaining results in a Word document, having a confusion matrix and accuracy of each algorithm. By comparing the results of the confusion matrix and accuracy score, the Random Forest Classifier and XGBoost demonstrate the highest accuracy scores, while Logistic Regression yields a lower accuracy score. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Smart Gauntlet to Assist Physically Challenged and Fragile Mortals

IoT-Based Smart Gauntlet to Assist Physically Challenged and...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： Thangam S Gurupriya M Kanderi Johith Kumar Kuthati Shreya Lasya Priya Divakarla Dept. of Computer Science and Engineering Amrita School of Computing Bengaluru India

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372823

Individuals who are bedridden or incapacitated struggle to do particular daily tasks because they have trouble with specific hand movements. Some people can need extra help to do jobs or communicate easily. In this situation, flex sensors and an Arduino microcontroller are two features that make IoT smart gloves useful. When a person moves their fingers, the sensors detect those motions, interpret the gestures, and provide the appropriate output to an LCD monitor. The buzzer will sound, the LED will glow, and the carer will receive an emergency alert in case of an emergency. With the assistance of the smart glove, the user can utilize hand motions to turn on the fan or light.

关键词： Temperature sensors Temperature measurement Pressure sensors Microcontrollers Sensor phenomena and characterization Message services Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

Iterative Risk Aware PRM Path Planning Algorithm for Autonomous Unknown Environments Exploration 10

Iterative Risk Aware PRM Path Planning Algorithm for Autonom...

引用

10th International Conference on Automation, Robotics, and Applications, ICARA 2024

作者： Bana, Fatemeh Rekabi Alsayed, Ahmad Krajnik, Tomas Arvin, Farshad Durham University dept. Computer Science Durham United Kingdom University of Manchester dept. Mechanical Engineering Manchester United Kingdom Artificial Intelligence Center Czech Technical University Prague Czech Republic

ISBN: (纸本)9798350394245

Autonomous area exploration is a critical application for various robotic systems, with micro-drones being particularly suited due to their high manoeuvrability and reliability. However, their limited operational time and computational power pose challenges for effective exploration. This paper introduces a risk-aware path-planning algorithm for micro-drones, pri-oritising energy efficiency by minimising travel distance. The algorithm, utilizing Monte-Carlo simulations and a risk-aware Probabilistic Roadmap (PRM) method, discretises the workspace and constructs a topological PRM graph to mitigate collisions. Simulation results demonstrate the algorithm's performance in unknown environments, approaching ideal exploration in known areas. Field experiments with Crazyflie micro-drones validate its practical implementation, enabling micro-drones to navigate unknown environments with an acceptable collision risk for efficient exploration in resource-constrained spaces. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Recognition of Human Anomalies Using Convolution Neural Network

Recognition of Human Anomalies Using Convolution Neural Netw...

引用

Advances in Data engineering and Intelligent Computing Systems (ADICS), International Conference on

作者： Teja Parella Balakrishna Ponnam Santhiya P Praveen. A Sujihelen. L dept. of Computer Science and engineering Sathyabama Institute of Science and Technology Chennai Tamilnadu India

ISBN: (数字)9798350364828

ISBN: (纸本)9798350364835

By instantly identifying suspicious occurrences, people, and things, smart CCTV systems greatly improve monitoring capacities. In this research, we investigate how to enhance CCTV video stream anomaly detection using state-of-the-art machine-vision and machine-learning techniques, namely UNET and ALEXNET. In contrast to more conventional methods that depend on supervised learning, this research makes use of uncontrolled and semi-supervised learning techniques to tackle the variety and complexity of anomalies. Using algorithms like UNET and ALEXNET, the system can learn to spot outliers on its own, with little to no help from humans. Because it can tell the difference between normal and abnormal situations, this method improves monitoring efficiency and decreases false alarms. In addition, the system maintains original quality for unusual occurrences while keeping typical video at a lower level, optimizing storage economy. By combining UNET and ALEXNET algorithms, smart CCTV systems may detect suspicious events before they happen, which increases security and allows for faster reactions to any dangers.

关键词： Training System performance Supervised learning Streaming media Semisupervised learning Recording Security

来源：评论

学校读者我要写书评

暂无评论

Neural Radiance Fields for Transparent Object Using Visual Hull

Neural Radiance Fields for Transparent Object Using Visual H...

引用

International Conference on Big Data and Smart Computing (BIGCOMP)

作者： Heechan Yoon Seungkyu Lee Dept. of Computer Science and Engineering Kyunghee University Yongin Republic of Korea

Unlike opaque object, novel view synthesis of transparent object is a challenging task, because transparent object refracts light of background causing visual distortions on the transparent object surface along the viewpoint change. Recently introduced Neural Radiance Fields (NeRF) is a view synthesis method. Thanks to its remarkable performance improvement, lots of following applications based on NeRF in various topics have been developed. However, if an object with a different refractive index is included in a scene such as transparent object, NeRF shows limited performance because refracted light ray at the surface of the transparent object is not appropriately considered. To resolve the problem, we propose a method based on NeRF, mathematical equations for the description of light refraction, and visual hull. Experimental evaluation results demonstrate that our method addresses the limitation of conventional NeRF with transparent objects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based Security System for Health Care

Blockchain Based Security System for Health Care

引用

Contemporary Computing and Communications (InC4), IEEE International Conference on

作者： Ankit Rishipal Singh Dept. of Computer Science & Engineering Guru Jambheshwar University of Science & Technology Hisar India

ISBN: (数字)9798350383652

ISBN: (纸本)9798350383669

Security in healthcare systems based on blockchain technology is the subject of ongoing research. Block Chain technology has the potential to revolutionize many different sectors since it provides a decentralized, incontestable, and publicly verifiable record of every transaction activity. Bitcoin's foundational mechanism is referred to as “block chain technology.” This technology allows for completely decentralized transaction processing. Healthcare aims to diagnose, treat, relieve, and cure any and all bodily and mental health issues, as well as to promote health and prevent sickness. Since all transactions in a blockchain are encrypted, it provides the highest level of security possible. Blockchain networks provide the same assurance of security for medical records. The integrity of the network's ledgers may be checked by checking file signatures on each node to make sure no alterations have been performed. The signature will no longer be valid when the record has been modified. The future of blockchain and big data applications is promising. Big Data technology can manage any kind, amount, or speed of data, while blockchain enhances efficiency across all industries. It has been noticed that medical records are maintained on a blockchain for reasons of security. Proposed system has evaluated healthcare data for security. When compared to the results of cutting-edge research, however, the scalability and adaptability of traditional methods are clearly lacking. Better performance and security utilizing blockchain technology is essential, hence developing such a system is a priority.

关键词： Industries Scalability Medical services Mental health Bitcoin Big Data applications Blockchains

来源：评论

学校读者我要写书评

暂无评论

Real Estate Price Prediction Using PySpark MLlib

Real Estate Price Prediction Using PySpark MLlib

引用

Smart Power Control and Renewable Energy (ICSPCRE), IEEE International Conference on

作者： Kadam Prajwal Dharmaraj Pradeep Kumar Gupta Keerthana Ajith Mahi Kolli Sangita Khare Niharika Panda Dept. of Computer Science and Engineering Amrita School of Computing Bengaluru India

ISBN: (数字)9798350377002

ISBN: (纸本)9798350377019

Prices of real estates in metropolitan landscapes harbour immense importance in steering the complexities of dynamic city environments. In India, the real estate sector contributes around 6–7% to India's GDP. Therefore, accurate forecasting of real estate prices is a factor in making informed decisions, affecting various stakeholders. Many techniques were used for this in past several years, like Hedonic models, Repeat-Sales models, Rule-Based Systems and Heuristics, etc. This study leverages the power of machine learning and big data to develop a robust framework for predicting housing prices in metropolitan landscapes. We employ PySpark, a powerful big data processing framework with built-in MLlib library (machine learning library), to analyse large-scale housing data encompassing various cities in India & to predict the prices for the same. By implementing a comparative analysis of prominent regression models - Random Forest, Linear Regression, Decision Tree, and Gradient-Boosted Tree - our approach identifies the most effective algorithms for real estate price prediction using MLlib library. Also, this study highlights the need for scalable solutions to manage an increasing number of data sources and emphasizes the PySpark library which will simplify big data handling and enable parallel computing. This study paves the way for utilizing advanced machine learning techniques and big data platforms to gain valuable insights into real estate markets. Our findings emphasize the critical role of combining these powerful tools to navigate the complex dynamics of urban housing and predict prices with greater accuracy.

关键词： Adaptation models Accuracy Machine learning algorithms Urban areas Predictive models Big Data Libraries

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：