检索结果-内蒙古大学图书馆

International Conference on Computational science and Computational Intelligence (CSCI)

作者： Weizheng Gao Jianning Su Olumide Malomo Julian Allagan Adeyemi Adekoya Ephrem Eyob Somasheker Akkaladevi Shanzhen Gao Department of Mathematics and Computer Science West Virginia State University Department of Mathematics and Sciences Midway University Department of Computer Information Systems Reginald F Lewis College of Business Virginia State University Department of Mathematics Computer Science and Engineering Technology Elizabeth City State University

Mathematicians and computer Scientists love Fibonacci numbers because the rule to generate the sequence is very simple, but they are related to many challenging conjectures. There are around 7300 items listed on Fibonacci numbers in the On-Line Encyclopedia of Integer Sequences [1]. In this paper, we will discuss some properties, algorithms and Python programs used to generate Fibonacci numbers, conjectures, and the applications of Fibonacci numbers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluating Machine Learning and Statistical Models for Greenland Subglacial Bed Topography 22

Evaluating Machine Learning and Statistical Models for Green...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Yi, Katherine Dewar, Angelina Tabassum, Tartela Lu, Jason Chen, Ray Alam, Homayra Faruque, Omar Li, Sikan Morlighem, Mathieu Wang, Jianwu Purdue University Department of Computer Science West LafayetteIN United States University of Oregon Department of Physics EugeneOR United States University of Maryland Baltimore County Department of Information Systems BaltimoreMD United States University of Maryland College Park Department of Information Studies College ParkMD United States Marriotts Ridge High School Ellicott City MarylandMD United States Texas Advanced Computing Center University of Texas at Austin AustinTX United States Dartmouth College Department of Earth Sciences HanoverNH United States

ISBN: (纸本)9798350345346

The purpose of this research is to study how different machine learning and statistical models can be used to predict bedrock topography under the Greenland ice sheet using ice-penetrating radar and satellite imagery data. Accurate bed topography representations are crucial for understanding ice sheet stability and vulnerability to climate change. We explore nine predictive models including dense neural network, long-short term memory, variational auto-encoder, extreme gradient boosting (XGBoost), gaussian process regression, and kriging based residual learning. Model performance is evaluated with mean absolute error (MAE), root mean squared error (RMSE), coefficient of determination (R2), and terrain ruggedness index (TRI). In addition to testing various models, different interpolation methods, including nearest neighbor, bilinear, and kriging, are also applied in preprocessing. The XGBoost model with kriging interpolation exhibit strong predictive capabilities but demands extensive resources. Alternatively, the XGBoost model with bilinear interpolation shows robust predictive capabilities and requires fewer resources. These models effectively capture the complexity of the terrain hidden under the Greenland ice sheet with precision and efficiency, making them valuable tools for representing spatial patterns in diverse landscapes. © 2023 IEEE.

关键词： Greenland Interpolation Machine Learning Applications Model Evaluation Subglacial Bed Topography

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Learning Method for Software Defect Prediction Targeting Ranking

An Ensemble Learning Method for Software Defect Prediction T...

引用

2025 2nd International Conference on Algorithms, Software Engineering and Network Security (ASENS)

作者： Xiaowei Zhao Lu Lu Weibiao Chen Jiahao Cheng Xinyan Yi School of Computer Science and Engineering South China University of Technology Guangzhou China Digital Research Department China Southern Power Grid Guangzhou China Pengcheng Laboratory Shenzhen China College of Mathematics and Informatics South China Agricultural University Guangzhou China

ISBN: (数字)9798331520298

ISBN: (纸本)9798331520304

Software defects pose a significant threat to system stability and user experience. Traditional defect prediction methods often fall short in practical testing scenarios. In response to this, we propose SeDI (Semantics-Enhanced DT-NN Integration), an ensemble learning approach for ordinary software defect prediction. SeDI integrates static software metrics with deep semantic features extracted from abstract syntax trees, leveraging a gradient boosting ranking model and a Multi-layer Perceptron to enhance ranking accuracy. The model's performance is evaluated using FPA and PD20 metrics, demonstrating superior ranking accuracy and improved performance in the top 20% of predicted modules.

关键词： Accuracy Source coding Semantics Predictive models Feature extraction Software User experience Ensemble learning Software measurement Testing

来源：评论

学校读者我要写书评

暂无评论

The Smart Application of Data Mining in the Detection of Fraudulent Transactions 3

The Smart Application of Data Mining in the Detection of Fra...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Bodhankar, Aniruddha Aswal, Upendra Singh Arivazhagn, D. Pund, Sachin S. Kulkarni, Nandini Chaturvedi, Sudhir Kumar Dr. Ambedkar Institute of Management Studies and Research- Nagpur Department of Data Science & Information Systems Nagpur India Shri Ramdeobaba College of Engineering and Management Department of Industrial Engineering Maharashtra Nagpur India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India Symbiosis International University Department of Symbiosis School of Planning Architecture and Design Nagpur Nagpur India Business School Academy of Maritime Education and Training Deemed to Be University Department of Amet Chennai India Upes Department of School of Engineering Dehradun India

ISBN: (纸本)9798350319125

Records mining is a powerful analytical device used to find out styles, correlations, and traits in large facts sets. Smart application of data mining methods within the detection of fraudulent transactions has finished an extensive quantity of success. It normally entails statistical algorithms, facts evaluation, and machine getting to know techniques to stumble on suspicious sports associated with fraud. Using statistics mining techniques, it's far possible to music the behaviour of clients, discover anomalous transaction styles and developments in huge datasets, come across frauds and generate signals on suspicious activities. It also allows to identify which forms of merchandise are frequently centered, which price methods are used, which places are problem to danger, and which traders have capacity credit card fraud. The utility of facts mining within the detection of fraudulent sports entails principal techniques. The first method makes use of conventional techniques used by banks, credit groups and other retailers, which includes account reconciliation, annualized billing and complex question processing. Those methods are used to generate reviews that are used by investigators to perceive probably suspicious activities. The second technique entails the usage of superior analytical techniques such as neural networks, decision timber, and clustering algorithms. These strategies have the functionality to stumble on facts irregularities in several conditions that were formerly unseen or unknown. © 2023 IEEE.

关键词： developments entails reconciliation statistics transaction

来源：评论

学校读者我要写书评

暂无评论

American gesture Language Detection Using Transfer Learning and Efficientnet B1 Technique

American gesture Language Detection Using Transfer Learning ...

引用

Recent Advances in science and Engineering Technology (ICRASET), International Conference on

作者： Basel A. Dabwan Mukti E. Jadhav Fekry A. Olayah Ahlam F. Shamsan Department of Information System AlBaydha University AlBaydha Yemen Department of Computer Science Shri Shivaji Science & Art College Buldhana India Department of Information System Najran University Kingdom of Saudi Arabia Department of Information Systems Applied College Najran University Kingdom of Saudi Arabia

Sign language is the primary form of Conveying messages to individuals with hearing impairments or speech limitations. Regular people frequently undervalue the importance of gesture language, which is the only form of communication for the deaf and mute communities. These people are suffering significant setbacks in their lives as a result of these restrictions or impairments, including unemployment, severe depression, and a number of other symptoms. They also employ gesture translators aid as a form of communication. However, paying these interpreters would be excessively expensive, so a cheap solution to the issue is required. In order to translate the visual hand dataset based on American Sign Language into written information, a system has been created. The dataset of American Sign Language has three more characters—"del," "nothing," and "space," in addition to 29 classes for each letter in the English sign language. The collection has 10,208 pictures in it. The dataset underwent testing with diverse pretrained models. The majority of them performed rather typically, and Derived from this finding, we built a CNN model with EfficientnetB1 scaling loaded with weights It underwent training utilizing the ImageNet model, maintaining uniform scaling across depth, breadth, and resolution of dimensions utilizing a straightforward yet incredibly effective compound coefficient. We demonstrated the efficacy of this strategy through the model’s results. The model achieved an accuracy rate of 99.98%, with a validation accuracy of 100%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TASK SELECTION AND ASSIGNMENT FOR MULTI-MODAL MULTI-TASK DIALOGUE ACT CLASSIFICATION WITH NON-STATIONARY MULTI-ARMED BANDITS

arXiv

引用

arXiv 2023年

作者： He, Xiangheng Chen, Junjie Schuller, Björn W. GLAM – Group on Language Audio & Music Imperial College London United Kingdom CHI – Chair of Health Informatics MRI Technical University of Munich Germany Department of Computer Science The University of Tokyo Japan

Multi-task learning (MTL) aims to improve the performance of a primary task by jointly learning with related auxiliary tasks. Traditional MTL methods select tasks randomly during training. However, both previous studies and our results suggest that such a random selection of tasks may not be helpful, and can even be harmful to performance. Therefore, new strategies for task selection and assignment in MTL need to be explored. This paper studies the multi-modal, multi-task dialogue act classification task, and proposes a method for selecting and assigning tasks based on non-stationary multiarmed bandits (MAB) with discounted Thompson Sampling (TS) using Gaussian priors. Our experimental results show that in different training stages, different tasks have different utility. Our proposed method can effectively identify the task utility, actively avoid useless or harmful tasks, and realise the task assignment during training. Our proposed method is significantly superior in terms of UAR and F1 to the single-task and multi-task baselines with p-values Copyright © 2023, The Authors. All rights reserved.

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

Reconstructing Sepsis Trajectories from Clinical Case Reports using LLMs: the Textual Time Series Corpus for Sepsis

arXiv

引用

arXiv 2025年

作者： Noroozizadeh, Shahriar Weiss, Jeremy C. Machine Learning Department School of Computer Science Heinz College of Information Systems and Public Policy Carnegie Mellon University PittsburghPA United States National Library of Medicine National Institutes of Health BethesdaMD United States

Clinical case reports and discharge summaries may be the most complete and accurate summarization of patient encounters, yet they are finalized, i.e., timestamped after the encounter. Complementary data structured streams become available sooner but suffer from incompleteness. To train models and algorithms on more complete and temporally fine-grained data, we construct a pipeline to phenotype, extract, and annotate time-localized findings within case reports using large language models. We apply our pipeline to generate an open-access textual time series corpus for Sepsis-3 comprising 2,139 case reports from the Pubmed-Open Access (PMOA) Subset. To validate our system, we apply it on PMOA and timeline annotations from I2B2/MIMIC-IV and compare the results to physician-expert annotations. We show high recovery rates of clinical findings (event match rates: O1-preview–0.755, Llama 3.3 70B Instruct–0.753) and strong temporal ordering (concordance: O1-preview–0.932, Llama 3.3 70B Instruct–0.932). Our work characterizes the ability of LLMs to time-localize clinical findings in text, illustrating the limitations of LLM use for temporal reconstruction and providing several potential avenues of improvement via multimodal integration. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

In Silico Identification and Characterization of Micropeptides with Potential Therapeutic Properties from Non-Coding DNA of E. Coli

SSRN

引用

SSRN 2024年

作者： Raj, Navya Lashari, Saima Anwar Revikumar, Amjesh Tahir, Muhammed Department of Health Informatics College of Health Sciences Saudi Electronic University Dammam Saudi Arabia Department of Information Technology College of Computing and Informatics Saudi Electronic University Dammam Saudi Arabia Kerala Genome Data Centre Kerala Development and Innovation Strategic Council Vazhuthacaud Kerala Thiruvananthapuram695014 India Department of Computer Science National University of Sciences and Technology Balochistan Campus Pakistan

During the last decade, the traditional drug discovery and development method has been highly benefited by the advancements of computer-aided approaches and synthetic biological techniques. Synthetic vaccines and drug candidates derived from diverse sources are now widely being approved for the treatment of various disease conditions. This work explored the potential of the unused non-coding regions of the bacterial genome to act as a template for the computational design of peptide drug candidates against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The exhaustive micropeptidome from the intergenic regions of the Escherichia coli (E. coli) genome was predicted computationally and their physicochemical properties were analysed. A machine learning model was employed to classify the micropeptide sequences. The drug-likeness of the micropeptides was predicted and those with drug-like properties were modeled ab initio and further studied for their inhibitory activity against nonstructural protein 1 (NSP1) from SARS-CoV-2 using a structure-based drug-designing approach. Molecular docking and molecular dynamics simulation were carried out to identify the best inhibitors that stably bind to NSP1. This study used a non-obvious source to identify micropeptide drug candidates with strong binding affinity for NSP1 that may be further taken for in vitro and in vivo validation against SARS-CoV-2. © 2024, The Authors. All rights reserved.

关键词： Escherichia coli

来源：评论

学校读者我要写书评

暂无评论

A Material Identification Approach Based on Wi-Fi Signal

引用

computers, Materials & Continua 2021年第12期69卷 3383-3397页

作者： Chao Li Fan Li Wei Du Lihua Yin Bin Wang Chonghua Wang Tianjie Luo Cyberspace Institute of Advanced Technology Guangzhou UniversityGuangzhou510700China PCL Research Center of Cyberspace Security Peng Cheng LaboratoryShenzhen518052China Department of Computer Science and Computer Engineering University of ArkansasFayetteville72701USA College of Electrical Engineering Zhejiang UniversityHangzhou310058China China Industrial Control Systems Cyber Emergency Response Team Beijing100040China

Material identification is a technology that can help to identify the type of target *** approaches depend on expensive instruments,complicated pre-treatments and professional *** is difficult to find a substantial yet effective material identification method to meet the daily use *** this paper,we introduce a Wi-Fi-signal based material identification approach by measuring the amplitude ratio and phase difference as the key features in the material classifier,which can significantly reduce the cost and guarantee a high level *** practical measurement of WiFi based material identification,these two features are commonly interrupted by the software/hardware noise of the channel state information(CSI).To eliminate the inherent noise of CSI,we design a denoising method based on the antenna array of the commercial off-the-shelf(COTS)Wi-Fi *** that,the amplitude ratios and phase differences can be more stably utilized to classify the *** implement our system and evaluate its ability to identify materials in indoor *** result shows that our system can identify 10 commonly seen liquids with an average accuracy of 98.8%.It can also identify similar liquids with an overall accuracy higher than 95%,such as various concentrations of salt water.

关键词： Internet of Things Wi-Fi signal channel state information material identification noise elimination

来源：评论

学校读者我要写书评

暂无评论

HRPE-Enhanced AI-Based 5G Indoor Localization in Presence of Specular and Dense Multipaths

HRPE-Enhanced AI-Based 5G Indoor Localization in Presence of...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Yuchen Shi Xiaoxiao Yang Yuying Sun José Rodríguez-Piñeiro Xueming Hong Tomás Domínguez-Bolaño Xuefeng Yin College of Electronics and Information Engineering Tongji University Shanghai China School of Elec. Science and Engineering Xiamen University China School of Informatics Xiamen University China CITIC Research Center & Department of Computer Engineering University of A Coruña Spain

Fifth generation (5G) communication systems are expected to provide an ubiquitous solution for indoor positioning, and deep neural networks (DNNs) have been recently proposed for this purpose. However, DNN-based positioning solutions are in general very dependent on the training data. In this paper, an architecture for positioning based on wireless signals is proposed, namely the SAGE-Enhanced CEAP (SE-CEAP). The architecture considers firstly an enhancement of the acquired Channel State Information (CSI) data by means of a high-resolution parameter estimation (HRPE) method, namely the space-alternating generalized-expectation maximization (SAGE) algorithm, and secondly a specifically designed DNN for localization, namely the CNN-Enblock AI Positioning (CEAP). The provided results, considering a realistic 5G New Radio (NR) deployment in an indoor scenario, show that the proposed architecture outperforms other classical DNN-based localization approaches, not only in localization accuracy, but also in generalizability of the results, which is a common drawback of DNN-based solutions.

关键词：

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：