检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Mishra, Ajit Kumar Verma, Vikash Manivannan, R. Kumar, N. Krishna Srividya, Mudunuru Sharma, Sanskriti IES College of Technology Department of Electrical & Electronics Engineering M.P Bhopal462044 India GGITS Dept of Artificial Intelligence & Machine Learning M.P Jabalpur India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology School of Computing Computer Science & Engineering TN Chennai India Guru Nanak Institutions Technical Campus Ibrahimpatam Dept.of CSE Telangana Hyderabad India MLR Institute of Technology Dept. of CSE Telangana Hyderabad India GGITS Dept of Computer Science & Business System M.P Jabalpur India

ISBN: (纸本)9798331539948

Modern artificial intelligence uses geographical data mining and regional analysis to analyze large datasets. Deep learning is a new geographic AI method. Example: Geographic Deep Mining Network (GDMN). The Spatial Feature Extractor (SFE), Temporal Geospatial Attention Mechanism (TGAM), and Geospatial Data Fusion Module (GDFM) comprise this technique. We examined six popular approaches and found GDMN performed best. It worked successfully for several reasons. GDMN always outperforms its competitors in memory, F1 score, IoU, training time, and inference time. This is always true. These findings suggest that GDMN might boost geospatial AI's data mining and location analysis abilities. After all the effort, we have developed a solid basis for location intelligence, making it useful in various subject areas. Because it's versatile, mapping specialists may use GDMN for better environmental monitoring or city development. Deep learning helps GDMN make better space choices and uncover insights in large, challenging data sets that no one knew about. GDMN's cutting-edge approaches make space and time research and prediction simpler. This wide perspective offers a more full and all-encompassing picture of today's challenges than previous techniques. This makes it impossible to overstate how significant this work is to location intelligence. Its unmatched research and insights usher in a new era. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Advertisement Design: A PIL-Based Approach for Quality and Performance Analysis

AI-Powered Advertisement Design: A PIL-Based Approach for Qu...

引用

Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), International Conference

作者： Harshitha Chilupuri G. Ramesh J. Praveen Venkataramaiah Gude Dept. of Artificial Intelligence and Machine Learning Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad India Dept. of Computer Science and Engineering Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad India Department of Electrical and Electronics Engineering Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad Telangana India GP Technologies LLC U.S.A.

ISBN: (数字)9798331515911

ISBN: (纸本)9798331515928

The paper presents the development of a Data Science solution that applies generative AI models in order to create high-quality images to be used in visual marketing and advertising. Using the Python library PIL (Pillow) along with machine learning frameworks, the solution combines predefined product images with the selected backgrounds, enhancing image synthesis techniques for more appealing and contextually relevant visuals. This leads to improved efficiency and effectiveness in the creation of content by automatically placing product images onto the background images used in marketing campaigns. The approach demonstrated a 98.06% SSIM (Structural similarity Index) score, indicating significant visual quality improvement. Initial results suggest a 15% enhancement in visual appeal compared to traditional image creation methods.

关键词： Visualization Image transformation Generative AI Data science Libraries Performance analysis Indexes Advertising Optimization Python

来源：评论

学校读者我要写书评

暂无评论

ClimateCast: ML-Powered Temperature Forecasting for North 24 Parganas

ClimateCast: ML-Powered Temperature Forecasting for North 24...

引用

Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA), International Conference on

作者： Abhirup Paria Anindya Ghatak Biswajit Jana Arpan Adhikary Priyanka Sen Ruma Das Dept. of Computer Sc. & Engg. (Artificial Intelligence & Machine Learning) Haldia Institute of Technology Haldia India School of Computer Sc. Engg. & Tech. Bennett University Greater Noida Uttar Pradesh Dept. of Computer Sc. & Engg. Haldia Institute of Technology Haldia India School of Applied Science & Humanities Haldia Institute of Technology Haldia India

ISBN: (数字)9798331517953

ISBN: (纸本)9798331517960

Global warming is increasing at a rapid rate. Several efforts are made to understand its influence worldwide and in particular regions as well. Therefore, temperature prediction has become one of the most important and influential research topics because of its application in agricultural, ecological, industrial, and environmental sectors. This study reviews dif-ferent machine learning algorithms for temperature prediction and observes their superiorities. The area of study was done in North 24 Parganas, West Bengal, India. Parameters used in the dataset of the North 24 Parganas include wind speed, different types of UV radiance, cloud amount, soil moisture, precipitation rate, surface pressure, and specific and relative humidity. The relevant features are chosen from all the parameters using feature selection. The feature selection technique used is SelectKBest, using Mutual Info Regression. The different ML models used are KNN Regression, Linear Regression (LR), Decision Tree Regression, Support Vector Regression, Random Forest Regression, LightGBM Regression, XGBoost Regression, AdaBoost Regression and Ridge Regression. The experimental results were evaluated using Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE) and R Squared (coefficient of determination). The result of this experiment revealed that XGBoost Regression has MAE, MSE, RMSE, and R Squared respectively 0.361, 0.273, 0.523, 0.989 followed by LightGBM Regression with MAE, MSE, RMSE and R squared followed by 0.366, 0.276, 0.526 and 0.988. These results show that XGBoost Regression possesses a high capability for temperature prediction

关键词： Support vector machines Temperature distribution machine learning algorithms Accuracy Wind speed Soft sensors Soil moisture Feature extraction Vectors Regression tree analysis

来源：评论

学校读者我要写书评

暂无评论

PsychBERT: A Mental Health Language Model for Social Media Mental Health Behavioral Analysis

PsychBERT: A Mental Health Language Model for Social Media M...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Vajre, Vedant Naylor, Mitch Kamath, Uday Shehu, Amarda Stone Bridge High School Ashburn United States Applied Machine Learning Smarsh Nashville United States George Mason University Dept. of Computer Science Fairfax United States

ISBN: (纸本)9781665401265

Mental health behaviors are now recognized as primary factors contributing to suicide. This paper puts forth a novel mental health language model to address mental health and makes several contributions. First, it proposes a taxonomy and puts forth a comprehensive dataset of social media text. Second, it proposes a two-stage framework, first discriminating text relevant to mental health from non-relevant text and then carrying out multi-class classification for detection of mental health behaviors. Third, it proposes a novel mental health language model, PsychBERT, which is pretrained on a large corpus of biomedical literature on mental health and social media data. Fourth, the framework additionally incorporates components that enhance its explainability. Our evaluation shows that the proposed framework is outperforms state-of-the-art methods and is interpretable. Pre-trained PsychBERT is made publicly available for the community at https://***/mnaylor/psychbert-cased. © 2021 IEEE.

关键词： Health

来源：评论

学校读者我要写书评

暂无评论

An end-to-end interpolated Automatic speech recognition system with punctuated transcripts for the Hindi language 6

An end-to-end interpolated Automatic speech recognition syst...

引用

6th International Conference on Computing, Communication and Security, ICCCS 2021

作者： Joshi, Saurav Kumar, Vishal Machine Learning Engineer Convin.ai India Research Group Dehradun India Bipin Tripathi Kumaon Institute of Technology Dept. of Computer Science and Eng. Dwarahat India

ISBN: (纸本)9781665440394

The Automatic Speech Recognition System (ASR) produces transcripts that often are misinterpreted and confuses the reader due to lack of context and punctuations. The presence of punctuation in the text improves readability and helps in better cognitive understanding. A wide variety of work has been done on English but Hindi which is the third-largest spoken language in the world, after English and Mandarin, still remains in the shadows. This paper aims to extend the technology to a wider section and introduces an end-to-end system, interpolating an automatic speech recognition system and natural language processing to produce high-quality punctuated transcriptions for the Hindi language. An ASR is implemented using the Kaldi toolkit leveraging the hybrid deep neural networks and the punctuation restoration is done with Bidirectional RNNs with an attention network. © 2021 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Variational Density Propagation Continual learning

arXiv

引用

arXiv 2023年

作者： Angelini, Christopher F. Bouaynaya, Nidhal C. Rasool, Ghulam Dept. of Electrical and Computer Engineering Rowan University GlassboroNJ United States Depts. of Machine Learning and Neuro-Oncology Moffitt Cancer Center & Research Institute TampaFL United States

Deep Neural Networks (DNNs) deployed to the real world are regularly subject to out-of-distribution (OoD) data, various types of noise, and shifting conceptual objectives. This paper proposes a framework for adapting to data distribution drift modeled by benchmark Continual learning datasets. We develop and evaluate a method of Continual learning that leverages uncertainty quantification from Bayesian Inference to mitigate catastrophic forgetting. We expand on previous approaches by removing the need for Monte Carlo sampling of the model weights to sample the predictive distribution. We optimize a closed-form Evidence Lower Bound (ELBO) objective approximating the predictive distribution by propagating the first two moments of a distribution, i.e. mean and covariance, through all network layers. Catastrophic forgetting is mitigated by using the closed-form ELBO to approximate the Minimum Description Length (MDL) Principle, inherently penalizing changes in the model likelihood by minimizing the KL Divergence between the variational posterior for the current task and the previous task’s variational posterior acting as the prior. Leveraging the approximation of the MDL principle, we aim to initially learn a sparse variational posterior and then minimize additional model complexity learned for subsequent tasks. Our approach is evaluated for the task incremental learning scenario using density propagated versions of fully-connected and convolutional neural networks across multiple sequential benchmark datasets with varying task sequence lengths. Ultimately, this procedure produces a minimally complex network over a series of tasks mitigating catastrophic forgetting. Copyright © 2023, The Authors. All rights reserved.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Policy-Guided Lazy Search with Feedback for Task and Motion Planning

arXiv

引用

arXiv 2022年

作者： Khodeir, Mohamed Sonwane, Atharv Hari, Ruthrash Shkurti, Florian Robot Vision and Learning Lab University of Toronto Robotics Institute Canada Dept. of Computer Science University of BITS Pilani India Dept. of Mathematical and Computational Sciences University of Toronto Canada

PDDLStream solvers have recently emerged as viable solutions for Task and Motion Planning (TAMP) problems, extending PDDL to problems with continuous action spaces. Prior work has shown how PDDLStream problems can be reduced to a sequence of PDDL planning problems, which can then be solved using off-the-shelf planners. However, this approach can suffer from long runtimes. In this paper we propose LAZY, a solver for PDDLStream problems that maintains a single integrated search over action skeletons, which gets progressively more geometrically informed, as samples of possible motions are lazily drawn during motion planning. We explore how learned models of goal-directed policies and current motion sampling data can be incorporated in LAZY to adaptively guide the task planner. We show that this leads to significant speed-ups in the search for a feasible solution evaluated over unseen test environments of varying numbers of objects, goals, and initial conditions. We evaluate our TAMP approach by comparing to existing solvers for PDDLStream problems on a range of simulated 7DoF rearrangement/manipulation problems. Code can be found at https://***/ learning-based-tamp. © 2022, CC BY.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Plant seedlings classification using transfer learning 2

Plant seedlings classification using transfer learning

引用

2nd IEEE International Conference on Electronic Engineering, ICEEM 2021

作者： Hassan, Esraa Shams, Mahmoud Hikal, Noha A. Elmougy, Samir Kafrelsheikh University Faculty of Artificial Intelligence Dept. of Machine Learning and Information Retrieval Kafrelsheikh Egypt Mansoura University Faculty of Computers and Information Dept. of Information Technology Mansoura35516 Egypt Mansoura University Faculty of Computers and Information Dept. of Computer Science Mansoura35516 Egypt

ISBN: (纸本)9781665418423

Agriculture is essential for human survival and remains a major economic driver in many countries around the world. Most of the living things around the world feed on vegetation produced by agriculture. Therefore, the researchers should work on developing agriculture using the most recent artificial intelligence approaches. The diagnosis of the plant diseases based on the leaf detection are currently utilized based on machine vision systems. The selective of weeding are more helpful and struggled to identify weeds on a reliable and accurate manner compared with the traditional classification workflows that are sluggish and error-prone results from classification expertise given small number of expert taxonomists. In this paper, an overview of recent attempts to classify species using computer vision and machine learning techniques are realized. It concentrates on identifying plant species using leaf images. We used a dataset containing 4, 275 images of 12 species at various growth stages. Furthermore, we present an architecture for plant seedling classification-based machine learning. Convolutional Neural Network (CNN) and transfer learning are utilized as a classification algorithm. The experimentations results based on these classifiers indicated that the proposed model achieved 0.9754, 0.9742, 0.9766, and 0.9754 in terms of Accuracy, Sensitivity, Specificity, and F-score, respectively. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Fast and Scalable Method for Inferring Phylogenetic Networks from Trees by Aligning Lineage Taxon Strings

arXiv

引用

arXiv 2023年

作者： Zhang, Louxin Abhari, Niloufar Colijn, Caroline Wu, Yufeng Dept. of Mathematics Centre for Data Science Machine Learning National University of Singapore 119076 Singapore Dept. of Mathematics Simon Fraser University BurnabyBCV5A 1S6 Canada Dept. of Computer Science and Engineering University of Connecticut StorrsCT06269 United States

The reconstruction of phylogenetic networks is an important but challenging problem in phylogenetics and genome evolution, as the space of phylogenetic networks is vast and cannot be sampled well. One approach to the problem is to solve the minimum phylogenetic network problem, in which phylogenetic trees are first inferred, then the smallest phylogenetic network that displays all the trees is computed. The approach takes advantage of the fact that the theory of phylogenetic trees is mature and there are excellent tools available for inferring phylogenetic trees from a large number of biomolecular sequences. A tree-child network is a phylogenetic network satisfying the condition that every non-leaf node has at least one child that is of indegree one. Here, we develop a new method that infers the minimum tree-child network by aligning lineage taxon strings in the phylogenetic trees. This algorithmic innovation enables us to get around the limitations of the existing programs for phylogenetic network inference. Our new program, named ALTS, is fast enough to infer a tree-child network with a large number of reticulations for a set of up to 50 phylogenetic trees with 50 taxa that have only trivial common clusters in about a quarter of an hour on *** Codes 05C30 © 2023, CC BY.

关键词： Phylogenetic

来源：评论

学校读者我要写书评

暂无评论

Road Condition Detection and Crowdsourced Data Collection for Accident Prevention: A Deep learning Approach

Road Condition Detection and Crowdsourced Data Collection fo...

引用

Workshops on Image Processing Theory, Tools and Applications, IPTA

作者： Md Saroar Jahan Mominul Islam Md Sanjid Hossain Jhuma Kabir Mim Mourad Oussalah Nasrin Akter Centre for Machine Vision and Signal Processing (CMVS) Faculty of ITEE University of Oulu Oulu Finland Dept. of CSE Daffodil International University Dhaka Bangladesh Computer Vision and Pattern Recognition LUT Univerity Lappeenranta Finland CMVS Faculty of ITEE University of Oulu Oulu Finland

Bangladesh is one of the countries struggling to prevent road accidents, which is a global cause for concern. An early warning system that indicates road conditions can contribute to the prevention task. For this purpose, a deep-learning based approach using a Convolutional Neural Network (CNN) to learn from random road images the safety factor is developed. This results in a three-class categorization: (i) Severely risky roads, (ii) Mildly risky roads, and (iii) Normal roads. The application of deep learning techniques in this study yields an accuracy of 95.5% in detecting problematic road conditions. Furthermore, based on the study’s findings, a mobile application has been developed. The app enables real-time crowdsourced data collection of road conditions and provides a platform for users to share this information in real-time with other drivers, thereby, contributing to prevent accidents and raise awareness among drivers and users by pinpointing the location of the risky road. Finally, crowdsourced data has been reused to update the trained model, which further improves the classifier accuracy.

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：