检索结果-内蒙古大学图书馆

An Automated Python Script for data Cleaning and Labeling using Machine Learning Technique

Informatica (Slovenia) 2023年第6期47卷 219-232页

作者： Oladipupo, Matthew Abiola Obuzor, Princewill Chima Bamgbade, Babatunde Joseph Olagunju, Kazeem M. Adeniyi, Abidemi Emmanuel Ajagbe, Sunday Adeola Department of Data Science School of Science Engineering and Environment University of Salford United Kingdom Jericho GRA Ibadan Nigeria Department of Computer Engineering Ladoke Akintola University of Technology LAUTECH Ogbomoso Nigeria Department of Computer Sciences Precious Cornerstone University Ibadan Nigeria Department of Computer & Industrial Production Engineering First Technical University Ibadan Nigeria

Every employee in the company who deals with data needs to have clean, noise-free data. Since data warehouses store and update enormous amounts of data from several sources, there is a potential that some of those references may contain inaccurate data. Due to the noise, inefficacy, and poor characterization of the vast amount of accessible data, as well as the ensuing insensitivity and inefficiencies of human data cleaning and labeling, the presentation of the data has become ambiguous, and the assessment of the information has become difficult. A hole in the creation of a better data analysis method was identified. This helped to guide the creation of a Python script for automatically cleaning and labeling data. The first step in the strategy used in this study to accomplish its goals and objectives was to obtain a financial dataset from the top database, "Kaggle". Create a machine learning (ML) approach in Python that intends to automate the financial dataset cleaning. This covers ingesting data, addressing incomplete data, addressing anomalies, one-hot wrapping and label encoding, extracting date and time values, and data normalization. Implementing an unsupervised machine learning method that attempts to automate financial dataset labeling (k-means). Using the method includes the elbow principle, k-means clustering, data modeling of "age" versus "arrival," dimensionality reductions, computer vision, and dataset categorizing using the groupings. An empirical assessment of the cleaned and labeled automated trading dataset utilizing a comparison of the cleaned dataset before and after PCA adoption. The results show that the developed ML technique not only improved the performance of the audit data used in this study, but also classified the data after cleaning it and removing the unpleasant section and incomplete data, as shown by the k-means segmentation result and grouping by PCA. © 2023 Slovene Society Informatika. All rights reserved.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Enhancing Computational Model for Human Motion Recognition Using Deep Learning

Enhancing Computational Model for Human Motion Recognition U...

引用

2024 IEEE International Conference on Intelligent Signal Processing and Effective Communication Technologies, INSPECT 2024

作者： Yadav, Ram Kumar Daniel, A. Kumar, Birendra Sakhare, Apeksha Moriwal, Rahul Pawar, Raju Amity university Gwalior Department of Computer Science and Engineering Gwalior India G H Raisoni college of engineering Department of Data Science Internet of Things and Cyber Security Nagpur India G H Raisoni college of engineering Department of Computer Science and Engineering Nagpur India

ISBN: (纸本)9798350379525

Human motion recognition (HMR) is a fundamental task in computer vision with applications in healthcare, surveillance, human-computer interaction, and intelligent environments. This paper proposes a better-performing model for HMR using VGG16 and starts the preprocessing on the diverse dataset of RGB images. Our meticulous process involves normalization, resizing, and then extracting images. These preparatory steps lay the foundation for robust model training. Exploration then takes two VGG16, EfficientNetB7 and ensemble VGG16-EfficientNet B7 deep learning architectures. © 2024 IEEE.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

A novel approach for image retrieval in remote sensing using vision-language-based image caption generation

引用

Multimedia Tools and Applications 2025年第6期84卷 2985-3014页

作者： Yadav, Prem Shanker Tyagi, Dinesh Kumar Vipparthi, Santosh Kumar Department of Computer Science and Engineering Malaviya National Institute of Technology Rajasthan Jaipur302017 India School of Artificial Intelligence and Data Engineering Indian Institute of Technology Ropar Punjab Rupnagar140001 India

Recent advancements in satellite technologies have resulted in the emergence of Remote Sensing (RS) images. Hence, the primary imperative research domain is designing a precise retrieval model for retrieving the most pertinent images based on the query. Present Remote Sensing Image Retrieval (RSIR) systems use visual descriptors to characterize the primitives (such as various land-cover types) that are visible in the images. However, the visual descriptors are inadequate for defining the complicated content of RS images. To solve this problem, a new model is devised for image retrieval based on image captions. The goal is to generate textual illustrations with captions to define relations amongst objects precisely. Here, image captioning is attained based on the vision-language pre-training model. The image captions are utilized for generating features like term frequency-inverse document frequency (TF-IDF), length of text, and Bag of Words. Meanwhile, query text is utilized wherein features like TF-IDF, text length, and Bag of Words are obtained. The similarity between query text features and the image captions features has been computed on the basis of a hybrid similarity measure wherein weights are tuned with the proposed Honey Badger Political Optimizer (HBPO) to retrieve the image. The proposed HBPO provided enhanced efficiency with elevated precision of 93.3%, recall of 93.7%, F1-score of 93.5%, and Recall-Oriented Understudy for Gisting Evaluation (ROUGE) of 0.441. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

The Hidden Influence of Latent Feature Magnitude When Learning with Imbalanced data 4th

The Hidden Influence of Latent Feature Magnitude When Learn...

引用

4th International Conference on Pattern Recognition and Artificial Intelligence, ICPRAI 2024

作者： Dablain, Damien A. Chawla, Nitesh V. Department Computer Science and Lucy Family Institute for Data and Society University of Notre Dame Notre DameIN46553 United States

ISBN: (纸本)9789819787012

Machine learning (ML) models have difficulty generalizing when the number of training class instances are numerically imbalanced. The problem of generalization in the face of data imbalance has largely been attributed to the lack of training data for under-represented classes and to feature overlap. The typical remedy is to implement data augmentation for classes with fewer instances or to assign a higher cost to minority class prediction errors or to undersample the prevalent class. However, we show that one of the central causes of impaired generalization when learning with imbalanced data is the inherent manner in which ML models perform inference. These models have difficulty generalizing due to their heavy reliance on the magnitude of encoded signals. During inference, the models predict classes based on a combination of encoded signal magnitudes that linearly sum to the largest scalar. We demonstrate that even with aggressive data augmentation, which generally improves minority class prediction accuracy, parametric ML models still associate a class label with a limited number of feature combinations that sum to a prediction, which can affect generalization. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of LoRa Antennae for Low-Cost IoT Deployments

Comparative Analysis of LoRa Antennae for Low-Cost IoT Deplo...

引用

2024 International Symposium on Networks, computers and Communications, ISNCC 2024

作者： MacKo-Dobrovic, Alexandria Verhosek, Justin Buxton, Joshua Krupp, Brian Baldwin Wallace University Computer Science Department Berea United States Case Western Reserve University Computer and Data Sciences Department Cleveland United States

ISBN: (纸本)9798350364910

As the use and application of Internet of Things (IoT) expands, the search for reliable, long-range, low-cost, and low-power communication between devices in order to provide real-time data is essential. Given these requirements, LoRa is a favorable choice for IoT devices that have a low-bandwidth requirement such as those used in sensing applications. However, the potential distance of LoRa can be misleading for projects that use popular boards and low-cost antenna options such as spring and simple copper wire antennas. In this paper, we investigate the potential distance using a variety of popular LoRa boards with different types of low-cost antennas. We provide an analysis using a variety of boards including a LoRa RFM9X board, LoRa RP2040 board, and a Raspberry Pi 3 with a LoRa HAT. We utilize a variety of antennas including a pigtail antenna, a directly soldered spring antenna, and a simple copper wire antenna including a dipole antenna. We hypothesized that the pigtail antenna would outperform the spring and simple copper wire antennae due to its higher cost. However, through a series of experiments conducted on our campus that test various distances and obstructions, our experiments reveal that in most cases the spring antenna yielded higher signal strength measured in RSSI. These results will benefit IoT enthusiasts, practitioners, and engineers to make informed decisions about the hardware they utilize, thereby enhancing the overall performance and reliability of LoRa-enabled devices in diverse environments. © 2024 IEEE.

关键词： Dipole antennas

来源：评论

学校读者我要写书评

暂无评论

computer Vision and Deep Learning-Based Model for Detecting Spoofed Faces in Images 2nd

Computer Vision and Deep Learning-Based Model for Detectin...

引用

2nd International Conference on data science and Network Engineering, ICDSNE 2024

作者： Salian, Gayathri P Rao, Manasa K Rashmi, M. Department of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India

ISBN: (纸本)9789819783359

In the modern era of smart applications, video data is critically important in various contexts. In most of these applications, cameras are frequently incorporated to facilitate authentication. As a result, face recognition is the biometric method most frequently employed to authenticate users in these applications. The vulnerability of face recognition systems to spoofing attacks grows in tandem with their increased usage. As a result, robust countermeasures are required. This paper presents an approach to face anti-spoofing through transfer learning and YOLOv8 optimization. Additionally, a custom dataset was constructed using images obtained from web cameras and an existing dataset to assess the proposed work’s real-time effectiveness. The proposed approach also adds a blurriness threshold during image capture to improve performance. With a mean Average Precision (mAP50) of 0.975, the experimental outcomes highlight the model’s effectiveness in detecting face spoofing. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Internet of Medical Things: A Revolution in Healthcare for Enhancing Cardiac Monitoring and Patient-Care Through Wearables 3

Internet of Medical Things: A Revolution in Healthcare for E...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Chhoton, Amit Chakraborty Sharma, Arvind K. Yogananda School of Artificial Intelligence Computers and Data Science Shoolini University Himachal Pradesh India Daffodil International University Department of Computer Science Dhaka Bangladesh

ISBN: (纸本)9798331518592

Wearables play an important role in parallel with IoT towards the era of healthcare and it has to be designed effectively providing workable solutions for all areas of other medical scopes. The fundamental objective of this technology kinship is to make smart healthcare services possible towards societal necessities. This paper conducts a systematic review on current medical applications with Wearable Internet of Things. The use of well-defined keywords for strict paper selection is a criterion in further comprehensive analysis with published scientific work. This paper synthesizes the current state of knowledge and Wearable Internet of Things applications to be used in early prognosis, diagnosis, treatments and patient monitoring more specifically in cardiovascular diseases. Of interest is the characteristics in terms of design and structure, as well as efficiency in reducing the current disparities in healthcare. Additionally, this paper presents potential lines of research and obstacles to be overcome before increasing implementation of Wearable Internet of Things devices in smart-healthcare. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

A Corpus-Based Auto-encoder-and-Decoder Machine Translation Using Deep Neural Network for Translation from English to Telugu Language

引用

SN computer science 2023年第4期4卷 354页

作者： Mahanty, Mohan Vamsi, Bandi Madhavi, Dasari Department of Computer Science and Engineering Vignan’s Institute of Information Technology (A) Visakhapatnam 530046 India Department of Artificial Intelligence and Data Science Madanapalle Institute of Technology and Science Madanapalle 517326 India Department of Computer Science and Engineering Sridevi Women’s Engineering College Hyderabad 500075 India

There is a huge demand for machine translation to design automated auto-encoders that can convert English to the Telugu language. Neural machine translation (NMT) is a new and effective technology that has significantly benefited traditional machine translation strategies. As a result, the primary goal of this work is to propose an auto-encoder–decoder-based deep neural network for translating English to the Telugu language. Deep neural networks are used for learning, where input language is supplied to the neural network following data processing and analysis. The neural network then does auto-tuning, which helps to improve the translation quality. This proposed work produces target sentences in the Telugu language, resulting in a higher Bilingual Evaluation Understudy (BLEU) Score and a lower Word Error Rate (WER). The BLEU finds the similarity of the translated text by Machine Translation models with high-quality references and WER finds better accuracy in identifying the target sentence. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Deep neural network Encoder-and-decoder English-to-Telugu Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Deciphering Student Coding Behavior: Interpretable Keystroke Features and Ensemble Strategies for Grade Prediction

Deciphering Student Coding Behavior: Interpretable Keystroke...

引用

2023 IEEE International Conference on Big data, Bigdata 2023

作者： Khan, Muhammad Fawad Akbar Edwards, John Bodily, Paul Karimi, Hamid Utah State University Department of Computer Science United States Utah State University Data Science and Applications Lab United States Idaho State University Department of Computer Science United States

ISBN: (纸本)9798350324457

Keystroke data in programming reveals intricate patterns that reflect the behavior of programmers. These patterns hold promise for predicting grades and other applications, providing insights into the skills of both proficient and less proficient programmers. Analyzing these patterns can yield tailored feedback for students who need support, enabling effective interventions. Our study utilizes a keystroke dataset from the CS1 (Introduction to computer science) course at Utah State University. We developed novel features by combining elements like key presses, timestamps, source locations, and programming terminology, drawing on prior research, our insights, and an analysis of programming behavior. An ensemble-based feature selection method identifies key features, which are then used in hyperparameter optimization and grade prediction with six classification and three regression algorithms. We categorized grades into three levels: Low, Average, and High. Despite challenges such as class imbalance, plagiarism, limited data per assignment, and the ceiling effect, we attained a notable weighted F1 score of 78%. We also introduce an ensemble classification strategy, merging Isolation Forest outlier detection with a refined Random Forest classifier, achieving 80% accuracy on our test set. Additionally, we provide a detailed interpretation of our features, supported by results and a case study of our dataset. This research aims to enhance computer science education at the undergraduate level, focusing on improving its overall quality. Code and data are available https://***/DSAatUSU/***. © 2023 IEEE.

关键词： Grade prediction Keystroke Machine learning Programming Python

来源：评论

学校读者我要写书评

暂无评论

Introducing the Hyperdynamic Adaptive Learning Fusion (HALF) model for superior predictive analytics in E-learning

引用

Neural Computing and Applications 2025年 1-21页

作者： Islam, Umar Alali, Ibrahim Khalil Alotaibi, Shoayee Dlaim Alzaid, Zaid Shah, Babar Ali, Ijaz Moreira, Fernando Department of Computer Science IQRA National University Swat Campus Peshawar Pakistan Department of Instructional Technology Jouf University Sakaka Saudi Arabia Department of Artificial Intelligence and Data Science University of Hail Hail Saudi Arabia Faculty of Computer Science and Information Systems Islamic University of Madinah Madinah42351 Saudi Arabia College of Technological Innovation Zayed University Dubai United Arab Emirates REMIT Portucalense University & IEETA Aveiro University Aveiro Portugal

Today’s complex world is defined by digital changes in educational paradigms to which E-learning has contributed significantly, and as such, accurate prediction methods are needed for student performance modeling. In this paper a new and complex model is proposed, namely the Hyperdynamic Adaptive Learning Fusion (HALF) model that leverages adaptive computing paradigms and artificial intelligence to build a fusion of learning that adapts to the new learning patterns. Many conventional predictive models employ linear and simplistic relationships to predict an outcome from an input;hence, they fail to decompose complex and heterogenic data patterns of educational data and also suffer from scalability issues for dealing with large volumes of data. To overcome these issues, the HALF model employs the relevant ensemble learning algorithms that consist of bagging, boosting, and an innovative adaptive fusion strategy that integrates base and adaptive models to achieve higher accuracy and resilience in the latter. In doing so, and by adopting the scientific method of working on trials and errors and rigorous assessment employing a database derived from the Open University VLE, the investigation presented in this paper provides compelling evidence of the HALF model’s superior efficacy, which yields an accuracy of 87%. 2%, precision of 85. 4% It has been proved that 3% of all students have significant learning disabilities, while the recall value is 89. 1%, surpassing traditional methods. The model’s equation can be easily applied to any variety of courses and of students, which makes it highly beneficial to educators and administrators;at the same time, the model is highly interpretable. Therefore, HALF model proves to be a revolutionary addition to the current kind of statistical modeling in E-learning that depicts student engagement pattern into more precise and accurate form, reduce biases in all way possible and provides solution that might help to improve the course outc

关键词： Contrastive Learning

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：