检索结果-内蒙古大学图书馆

2024 International Conference on Communication, computer sciences and Engineering, IC3SE 2024

作者： Bharti, Dilip Kumar Singh, Sanjay Kumar Kumar, Mukesh Kanaujia, Vishal Kumar Aeri, Manisha Abes Engineering College Computer Science And Engineering-Data Science Ghaziabad India Kashi Institute Of Technology Department Of Computer Science & Applications Mirzamurad U.P Varanasi India Graphic Era Hill University Computer Science And Engineering Uttarakhand Dehradun248002 India Abes Engineering College Computer Science And Engineering Data Science Department Ghaziabad India

ISBN: (纸本)9798350366846

Diffusion tensor imaging (DTI) is a neuroimaging approach that lets in for the visualization and quantification of the structural integrity of white depend fibers in the brain. In latest years, DTI has come to be an essential tool for investigating the underlying neurobiological mechanisms of autism spectrum sickness (ASD), a neurodevelopmental disorder characterized via problems in social communication and repetitive behaviors. Through the usage of DTI, researchers have identified good sized styles of structural abnormalities in the brains of individuals with ASD. these abnormalities encompass changes in the microstructure of white remember fibers, along with decreased fiber density, changes in fiber directionality, and decreased connectivity between mind areas. Additionally, there may be evidence of bizarre mind development in early formative years, with a few research finding that these structural variations are present even in very younger children with ASD. One constant finding in DTI studies of ASD is reduced white rely integrity inside the corpus callosum, a large fiber package deal that connects the two hemispheres of the mind. This abnormality has been connected to deficits in social communiqué and language in people with ASD, as well as difficulties in integrating records from distinctive brain areas. The results showed extensive structural abnormalities in people with ASD in comparison to TD individuals. © 2024 IEEE.

关键词： Diffusion tensor imaging

来源：评论

学校读者我要写书评

暂无评论

A study on the prediction of software faults using RNN and LSTM 29

A study on the prediction of software faults using RNN and L...

引用

29th ISSAT International Conference on Reliability and Quality in Design, RQD 2024

作者： Song, Kwang Yoon Kim, Youn su Chang, In Hong Department of Computer Science and Statistics Chosun University Gwangju Dong-gu Korea Republic of

ISBN: (纸本)9798986576138

Software reliability has been continuously researched to solve the problem because software that plays a big role in various fields can cause big problems if it faults due to small or large problems such as coding or operation errors. Many software reliability models developed are based on NHPP, but since it is developed based on assumptions, it does not show good results for models that do not include assumptions. Therefore, in this study, we proposed a software reliability model using deep learning that does not rely on assumptions but on data. We utilized RNN and LSTM to solve the sequential nature of software reliability model using deep learning. We showed the superiority of software reliability models using deep learning by utilizing four measures using NTDS data. In particular, the software reliability model using LSTM showed excellent results. © Conference Proceedings of the 29th ISSAT International Conference on Reliability and Quality in Design, RQD 2024.

关键词： data reliability

来源：评论

学校读者我要写书评

暂无评论

Permutation Tests for the Partial Coefficient in a Multiple Linear Regression 1

引用

Asia-Pacific Conference on Applied Mathematics and statistics, APCAMS 2023

作者： Zhang, Shunpu Department of Statistics and Data Science University of Central Florida OrlandoFL32816-2370 United States

ISBN: (数字)9789819744381

ISBN: (纸本)9789819744374

Existing permutation tests for the partial coefficient in a multiple linear regression model are mostly stepwise algorithms which are difficult to be analyzed and compared theoretically. In this paper, we propose a unified framework for testing the partial coefficient in a multiple linear regression model. The unified framework provides a theoretical basis for constructing permutation tests for the partial coefficient as well as theoretical justifications why they work. As a result, several permutation tests are proposed based on the unified framework. The unified framework also enables us to compare the performances of the permutation tests theoretically. By showing that the existing permutation tests for the partial coefficient of a multiple linear regression model are special cases of the unified framework, we are able to identify redundant steps and provide simpler algorithms for the existing permutation tests. Recommendations on which methods to use under different situations are provided based on the theoretical and numerical comparisons we have conducted. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

Leveraging LLMs for Integrated Sentiment and Topic Analysis on African Social Media 23

Leveraging LLMs for Integrated Sentiment and Topic Analysis ...

引用

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Sibitenda, Harriet Hu, Ruofan Rundensteiner, Elke Diattara, Awa Traore, Assitan Ba, Cheikh University of Gaston Berger Computer Science Department Saint Louis Senegal Data Science Program Worcester Polytechnic Institute Worcester United States Data Science Program Worcester Polytechnic Institute Worcester United States Actroll Data Science Department France

ISBN: (纸本)9798350374889

Leveraging AI to analyze key topics on African social media can enhance public governance. Our study analyzes social media discourse within African society on development concerns by (1) evaluating AI techniques for sentiment, topic, and theme extraction, comparing the accuracy of these methods with human annotations, and (2) extracting key insights from the data to provide policymakers with actionable recommendations for sustainable development. For this study, we utilized a data corpus of 22,036 posts from Twitter and YouTube, all focused on development issues in Africa. We applied topic modeling to extract relevant topics from the corpus and used similarity analysis, powered by Large Language Models, to link these topics to prevalent development themes. Additionally, we leveraged unsupervised models such as VADER and Large Language Models to extract sentiment related to the identified topics. To validate these model-generated sentiments, we conducted a small crowdsourced study to gather human-annotated labels as ground truth. Our sentiment analysis findings show improvements with models like TextBlob, VADER, and Llama. Fine-tuning, partic-ularly with BERT, achieved an impressive Fl score of 0.988. Meanwhile, Llama demonstrated strong precision (0.72) and balanced accuracy (0.55) in capturing contextual sentiment. We identified 304 topics using BERTopic and Llama, with robust coherence (0.81 C-v) and divergence (0.58 IRBO). In theme analysis, the One-vs-Rest classification with ensemble voting performed exceptionally well, with 'Poverty' achieving the highest F1 score of 0.89. Our results suggest that African policymakers prioritize addressing corruption, unemployment, drought, and instability, while closely monitoring the positive impacts of policy interventions. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Navigating the global stock market: correlation, prediction, and the influence of external factors

引用

Iran Journal of computer science 2024年第3期7卷 397-422页

作者： Islam, Mohammad Shariful Rony, Mohammad Abu Tareq Computer Science and Telecommunication Engineering (CSTE) Noakhali Science and Technology University Noakhali 3814 Bangladesh Department of Statistics Noakhali Science and Technology University Noakhali 3814 Bangladesh

Assessing a country’s economic health is a complex task that involves predicting stock price movements. The prices of stocks reflect the overall business climate and the performance of companies. This study examines the relationship between external factors such as weather conditions and pandemic-related data during COVID-19 and global stock prices to enhance comprehension of how worldwide occurrences impact the stock exchange. The analysis reveals that external factors influence stock prices differently, but correlations can provide valuable insights into market dynamics. The research focuses on daily time-series data for various stock indices, including NYSE COMPOSITE, TSX Composite, Nikkei 225, Global X DAX Germany, and HANG SENG INDEX, as well as weather and COVID-19 data. By identifying characteristics that can be correlated with financial market data, the study finds that some factors derived from COVID-19 and weather data have a strong and moderate correlation with daily stock prices. However, it’s important to note that correlation does not necessarily imply causation, even though these insights can be helpful to investors and researchers. For this, the study employs various machine learning and deep learning models to gain a deeper understanding of stock market dynamics in the context of global events. Linear Regression is identified as the top-performing model for NYSE COMPOSITE and TSX Composite in Canada, as well as Germany’s DAX index, with exceptional predictive accuracy. Gradient Boosting Regression proves effective for Japan’s Nikkei 225 index and China’s Hang Seng Index. These findings can be valuable tools for financial analysts and investors who want to enhance their predictive abilities. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： External factors Pandemic effect Price prediction Stocks Weather

来源：评论

学校读者我要写书评

暂无评论

High dimensional logistic regression under network dependence

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 20119-20180页

作者： Somabha Mukherjee Ziang Niu Sagnik Halder Bhaswar B. Bhattacharya George Michailidis Department of Statistics and Data Science National University of Singapore Singapore Department of Statistics and Data Science University of Pennsylvania Philadelphia Department of Statistics University of Florida Gainesville Department of Statistics and Data Science University of California Los Angeles Los Angeles

Logistic regression is a key method for modeling the probability of a binary outcome based on a collection of covariates. However, the classical formulation of logistic regression relies on the independent sampling assumption, which is often violated when the outcomes interact through an underlying network structure, such as over a temporal/spatial domain or on a social network. This necessitates the development of models that can simultaneously handle both the network 'peer-effect' (arising from neighborhood interactions) and the effect of (possibly) high-dimensional covariates. In this paper, we develop a framework for incorporating such dependencies in a high-dimensional logistic regression model by introducing a quadratic interaction term, as in the Ising model, designed to capture the pairwise interactions from the underlying network. The resulting model can also be viewed as an Ising model, where the node-dependent external fields linearly encode the high-dimensional covariates. We propose a penalized maximum pseudo-likelihood method for estimating the network peer-effect and the effect of the covariates (the regression coefficients), which, in addition to handling the high-dimensionality of the parameters, conveniently avoids the computational intractability of the maximum likelihood approach. Under various standard regularity conditions, we show that the corresponding estimate attains the classical high-dimensional rate of consistency. In particular, our results imply that even under network dependence it is possible to consistently estimate the model parameters at the same rate as in classical (independent) logistic regression, when the true parameter is sparse and the underlying network is not too dense. Consequently, we derive the rates of consistency of our proposed estimator for various natural graph ensembles, such as bounded degree graphs, sparse Erdős-Rényi random graphs, and stochastic block models. We also develop an efficient algorithm for computi

关键词： high-dimensional inference ising models logistic regression Markov random fields network data penalized regression pseudo-likelihood random graphs

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Effectiveness of Deep Convolutional Neural Networks for Picture Quality Prediction 27

Evaluating the Effectiveness of Deep Convolutional Neural Ne...

引用

27th International Symposium on Wireless Personal Multimedia Communications, WPMC 2024

作者： Jhingran, Sushant Chaturvedi, Rekha Bansal, Nidhi Malik, Suraj Sharda University Department of Computer Science and Engineering Greater Noida India Manipal University Jaipur School of Information Security and Data Science Department of Data Science and Engineering Rajasthan Jaipur India Pune India IIMT University Department of Computer Science and Engineering Uttar Pradesh Meerut India

ISBN: (纸本)9798350392319

Since the advent of smartphones, capturing images has become deeply embedded in human behavior, evolving into a fundamental part of daily life. Research into human perception of image quality is crucial as people frequently acquire and interpret images. Automation in image processing systems is vital for quantifying image quality, addressing issues like blurriness, noise, and compression that can significantly degrade the visual experience. While image processing professionals can quickly identify such distortions, integrating human visual perception into automated system design remains challenging. Consequently, machine-based evaluation of image quality is a critical research area. Image quality assessment algorithms aim to approximate human visual judgments. Although deep learning has shown remarkable success in various real-world tasks, such as object detection and image classification, its application in image quality assessment is still evolving. The primary challenge is assessing image quality without explicitly considering human perception, making it a dynamic area of ongoing research. A significant hurdle is the lack of images with quality scores, particularly differential average feedback scores provided by image quality experts on a 1-100 scale. This limitation hinders the development of robust models for image quality assessment, highlighting the need for innovative solutions in this evolving research domain. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Flow-Guided Deformable Alignment Network with Self-Supervision for Video Inpainting 48

Flow-Guided Deformable Alignment Network with Self-Supervisi...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wu, Zhiliang Zhang, Kang Sun, Changchang Xuan, Hanyu Yan, Yan Nanjing University of Science and Technology School of Computer Science and Engineering China Illinois Institute of Technology Department of Computer Science United States Anhui University School of Big Data and Statistics China

ISBN: (纸本)9781728163277

Video inpainting aims to utilize plausible contents to fill missing regions in the video. State-of-the-art video inpainting methods typically generate the missing contents of the target frame (current frame) by aggregating the temporal information of reference frames (neighboring frames) aligned using deformable convolution. However, these deformable convolution alignment networks often suffer from offset overflow during training, resulting in unsatisfactory alignment, thereby obtaining compromised inpainting performance. In this paper, we propose a self-supervised Flow-Guided Deformable Alignment (FGDA) network for aligning reference frames at the feature level. FGDA computes the residual of the optical flow as the offsets. This design can effectively reduce the burden of offsets learning, thereby avoiding offset overflow. Furthermore, a gradient-weighted reconstruction loss for supervised completed frame reconstruction is designed, which can use the gradients in all directions of the video frame to emphasize the difficultly reconstructed texture regions, so that detail textures get more attention during training. Experiments show that FGDA-based video inpainting model trained with gradient-weighted reconstruction loss outperforms the state-of-the-art by a significant margin in terms of PSNR and SSIM with relative improvements of 6.2% and 2.1%, respectively. © 2023 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Prediction of Alzheimer'S Disease from Magnetic Resonance Images (MRI) 5

Prediction of Alzheimer'S Disease from Magnetic Resonance Im...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Manimuthu, A. Peter Jose, P. Gangadevi, E. Kumar, U.Udhaya Anandaraj, M.D. Loyola College Department of Data Science Chennai India Mount Carmel College Department of Computer Science Bangalore India Loyola College Department of Computer Science Chennai India Shanmuga Industries Arts & Science College Department of Mca Tamil Nadu India

ISBN: (纸本)9798350383522

Alzheimer's disease (AD) is an enigmatic, neurodegenerative brain disorder that impairs memory, concentration, and even basic tasks. Every three seconds, a new AD case emerges worldwide, underscoring its widespread impact. Extensive research underscores the pivotal role of early AD detection in curtailing treatment expenses and duration. This study pioneers a dual approach, leveraging both Machine Learning and Deep Learning methodologies to prognosticate Alzheimer's through MRI images. Notably, the VGG16-based model achieves an impressive accuracy of 0.808, surpassing conventional machine learning models (SVM, RF, KNN, DT, NB, LR) and sophisticated deep learning counterparts (CNN, VGG16, ResNet50, MobileNet, DenseNet 121). This outcome presents a pivotal stride toward advancing Alzheimer's diagnosis and optimizing treatment strategies for enhanced patient care. © 2024 IEEE.

关键词： Alzheimer's Disease Deep Learning Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural network-based image watermarking using discrete wavelet transform

引用

International Journal of Information Technology (Singapore) 2023年第4期15卷 2021-2029页

作者： Tavakoli, Alireza Honjani, Zahra Sajedi, Hedieh Department of Computer Engineering School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Department of Computer Science School of Mathematics Statistics and Computer Science College of Science University of Tehran Tehran Iran

With the growing popularity of the Internet, digital images are used and transferred more frequently. Although this phenomenon facilitates easy access to information, it also creates security concerns and violates intellectual property rights by allowing illegal use, copying, and digital content theft. Using watermarks in digital images is one of the most common ways to maintain security. Watermarking is proving and declaring ownership of an image by adding a digital watermark to the original image. Watermarks can be either text or an image placed overtly or covertly in an image and are expected to be challenging to remove. This paper proposes a combination of convolutional neural networks (CNNs) and wavelet transforms to obtain a watermarking network for embedding and extracting watermarks. The network is independent of the host image resolution, can accept all kinds of watermarks, and has only 11 layers while keeping performance. Performance is measured by two terms;the similarity between the extracted watermark and the original one and the similarity between the host image and the watermarked one. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Convolutional neural networks Neural networks Watermarking Wavelet transform

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：