检索结果-内蒙古大学图书馆

artificial intelligence and data science Based R&D Interventions 1

1000年

作者： Ratnajit Bhattacharjee Debanga Raj Neog Konda Reddy Mopuri Santosh Kumar Vipparthi

This book title is a composition of multiple research efforts that are based on cutting-edge artificial intelligence (AI) techniques. Some of the signal processing problems are addressed with techniques from the broad... 详细信息

ISBN: (数字)9789819926091

ISBN: (纸本)9789819926084;9789819926114

关键词： artificial intelligence data Structures and Information Theory Natural Language Processing (NLP) Signal, Image and Speech Processing

来源：评论

学校读者我要写书评

暂无评论

data science and artificial intelligence for Life science at the University of Trieste

Data Science and Artificial Intelligence for Life Science at...

引用

2023 Italia Intelligenza artificiale - Thematic Workshops, Ital-IA 2023

作者： Barbati, Giulia Borbussi, Luca Caravagna, Giulio Artificial Intelligence and Cyber Physical Systems Laboratory Department of Mathematics and Geoscience University of Trieste Italy Cancer Data Science Laboratory Department of Mathematics and Geoscience University of Trieste Italy

This document reports data science and artificial intelligence initiatives oriented towards Life sciences applications that are in place at the Trieste node for the national AIIS Laboratory. © 2023 Copyright for ... 详细信息

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

CoverGAN: cover photo generation from text story using layout guided GAN

引用

Soft Computing 2025年第1期29卷 405-423页

作者： Cheema, Adeel Naeem, M. Asif Department of Data Science and Artificial Intelligence National University of Computer and Emerging Sciences Islamabad Pakistan

Generating cover photos from story text is a non trivial challenge to solve. Existing approaches focus on generating only images from given text prompt. To the best of our knowledge, non of these approaches focus on generating cover photos from a text story. The paper addresses this issue by introducing multi-object image generation with text title from a text story. We split the problem into three steps:- understanding semantics of text story, predicting layout of objects, and generating a cover photo. At start, a semantic relation was encoded between text story objects using a Scene graph, then features from graph neural network were concatenated with single object features from scene graph to create an object layout. All of these features were then passed on to the image generating part. Image generation was further divided into two phases. In the first phase, the image is generated using a scene graph image generation model. While in the second phase, the results of first phase were further enhanced using image translation model conditioned on the object layout. In final phase we generated title of the given story based on generated image. In our experiments, we used custom dataset of text stories with three animal categories along with the COCO dataset. For the image generating part, we evaluated our approach with state of the art models known as scene_gen and sg2im. Our method generated high-resolution informative cover photo with story title by positioning the objects at right locations as specified in the text story. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Automated Inter-Hospital Communication for Bed Allocation 4

Automated Inter-Hospital Communication for Bed Allocation

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Akila Priya Varshini, M. Kashvi, R. Pushpa Varshini, A. Nirmala, V. Vidhya, V. Dept of Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798331523923

This paper presents an automated inter-hospital communication system for efficient bed allocation during pandemics, featuring role-based access for secure data handling. The system leverages real-time data integration, predictive analytics, and AI-driven optimization to streamline bed allocation across hospitals. The role-based access makes sure that only authorized personnel can access information, enhancing data security and operational transparency. This approach addresses common inefficiencies in current systems, reducing patient wait times and improving resource management in high-demand scenarios, ultimately enhancing crisis response capabilities. © 2025 IEEE.

关键词： data integration

来源：评论

学校读者我要写书评

暂无评论

An optimized ensemble model based on meta-heuristic algorithms for effective detection and classification of breast tumors

引用

Neural Computing and Applications 2025年第6期37卷 4881-4894页

作者： Saber, Abeer Elbedwehy, Samar Awad, Wael A. Hassan, Esraa Information Technology Department Faculty of Computers and Artificial Intelligence Damietta University Damietta34517 Egypt Department of Data Science Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33511 Egypt Department of Computer Science Faculty of Computers and Artificial Intelligence Damietta University Damietta34517 Egypt Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33511 Egypt

One of the most common cancers among women worldwide is breast cancer (BC), and early diagnosis can save lives. Early detection of BC increases the likelihood of a successful outcome by enabling treatment to start sooner. Even in areas without access to a specialist physician, machine learning (ML) aids in early BC detection. The medical imaging community is becoming more interested in using ML, and deep learning (DL) to increase the accuracy of cancer screening. Many disease-related data are sparse. However, for DL models to perform well, a large amount of data is required. Because of this, the DL models that are currently in use on medical images are not as effective as they could be. Convolutional neural network (CNN) models have recently gained popularity in the medical industry, and they perform admirably in terms of high performance and robustness at image classification. The proposed method classifies data using ensemble pre-trained models such as the dense convolutional network (DenseNet)-121 and EfficientNet-B5 feature extractor networks, as well as the support vector machine for classification. Using a modified meta-heuristic optimizer, the selected pre-trained CNN hyperparameters were optimized to improve the performance. The experimental results for the presented model on the INbreast dataset show that the EfficientNet-B5 model is effective for BC classification, with overall accuracy, sensitivity, specificity, precision, and area under the ROC curve (AUC) values of 99.9%, 99.9%, 99.8%, 99.1%, 1.0, respectively. © The Author(s) 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Image Recognition for Wildlife Conservation

Image Recognition for Wildlife Conservation

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Charanya, P. Sridharan, S. Yuvan Shankar, S. Sriram, M. Yashvanth, K.P. Department of Artificial Intelligence and Machine Learning Coimbatore India Department of Artificial Intelligence and Data Science Coimbatore India

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512965

This study adopts an empirical approach to evaluate the efficacy of image processing methods in conservation efforts for animals. The initial phase involves the collection of data from various sources within the natural ecosystem, including images captured through camera traps, drones, and other monitoring devices. This comprehensive and diverse dataset is then processed using advanced Image Processing Tools. A key strength of this methodology lies in its use of Machine Learning algorithms, particularly YOLO v8 (You Only Look Once) and Support Vector Machines (SVMs). These techniques are suitable for wildlife conservation because of their capacity to analyze complex visual data and detect patterns indicative of species presence, behavior, and habitat conditions. The paper outlines the application of YOLO v8 and SVMs to the collected image data, enabling accurate identification, real-time detection, and classification of wildlife species. This capability is essential for monitoring populations, tracking movements, and identifying potential threats, thus facilitating timely conservation actions. Furthermore, the research extends its evaluation by comparing the results of the Machine Learning approach with traditional ecological survey methods, offering a comprehensive assessment of the effectiveness of image processing in wildlife conservation. © 2025 IEEE.

关键词： Invertebrates

来源：评论

学校读者我要写书评

暂无评论

Answer to "comments on an examination of daily CO2 emissions prediction through a comparative analysis of machine learning, deep learning, and statistical models"

引用

Environmental science and Pollution Research 2025年第12期32卷 7793-7794页

作者： Ajala, Adewole Adetoro Centre of Excellence for Data Science Artificial Intelligence & Modelling University of Hull Hull United Kingdom

来源：评论

学校读者我要写书评

暂无评论

A BERT-Based Model to Analyse Disaster’s data for Efficient Resource Management

引用

SN Computer science 2025年第2期6卷 1-15页

作者： Lamba, Sonu Vidyarthi, Pranav Aggarwal, Mudit Gangawar, Priyanshi Mulapalli, Snehita Artificial Intelligence and Data Science Gati Shakti Vishwavidyalaya Gujrat Vadodara 390004 India

In times of emergency, such as natural disasters, emergencies, pandemics, etc., the victims require rapid aid and resources. The response must be timely and effective, followed by swift recovery management. In recent years, the widespread use of online social media platforms has been phenomenal and has shaped the world around us at an unprecedented rate. We propose to build a model to provide a real-time disaster management strategy that collects data about the natural disaster from social media, verifies it, and classifies it for the need or availability of resources. Furthermore, make the information available to organizations that supply the necessary goods and services. The study uses social media data for two categorization tasks: one for classification of tweets connected to disaster and other for needs assessments. Primarily, tweets fetched from the Twitter (X) streaming API undergo a number of preprocessing stages. Term frequency and inverse document frequency (TF-idf), is then used to convert the data into vector matrices that are needed for the training model. Several machine learning techniques are then deployed for classifying disaster-related tweets. Afterwards, the tweets associated with positive class are further processed, analyzed, and classified for the need or availability of resources. Additionally, to improve the accuracy of the classification, we proposes a BERT (Bi-directional Encoded Representations for Transformers) based Tweets classification and Need Analysis models. The proposed BERT-based model is experimentally evaluated by comparing the prediction outcomes with various machine learning models. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： BERT Disaster management TF-IDF Tweets

来源：评论

学校读者我要写书评

暂无评论

Cross-Lingual Sentence Compression for Length-Constrained Subtitles in Low-Resource Settings 31

Cross-Lingual Sentence Compression for Length-Constrained Su...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Jørgensen, Tollef Emil Mengshoel, Ole Jakob Norwegian University of Science and Technology Data and Artificial Intelligence Group Norway

ISBN: (纸本)9798891761964

This paper explores the joint task of machine translation and sentence compression, emphasizing its application in subtitle generation for broadcast and live media for low-resource languages and hardware. We develop CLSC (Cross-Lingual Sentence Compression), a system trained on openly available parallel corpora organized by compression ratios, where the target length is constrained to a fraction of the source sentence length. We present two training methods: 1) Multiple Models (MM), where individual models are trained separately for each compression ratio, and 2) a Controllable Model (CM), a single model per language using a compression token to encode length constraints. We evaluate both subtitle data and transcriptions from the EuroParl corpus. To accommodate low-resource settings, we constrain data sampling for training and show results for transcriptions in French, Hungarian, Lithuanian, and Polish and subtitles in Albanian, Basque, Malay, and Norwegian. Our models preserve high semantic meaning and metric evaluations for compressed contexts. © 2025 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Reliable Roadside Assistance and Fast Solutions for Emergency Breakdown States by EF-YOLOv8m 4

Reliable Roadside Assistance and Fast Solutions for Emergenc...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Angeljulie, J. Pradish Pranam, S. Yosuva, B. Shuaib Khan, S. Coimbatore India Kahe Dept of Artificial Intelligence & Data Science India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523923

In the technological development era and fast-paced world, artificial intelligence techniques and Computer Vision algorithms are transfiguring the automotive industrial services, especially in reliable roadside assistance and emergency services for vehicle breakdowns. Significant AI-oriented algorithms including predictive maintenance, route optimization, resource allocation, and reinforcement learning techniques are used to address crucial problems like optimized resource distribution, rapid response, and proactive fault detection. This article incorporates AI-oriented algorithms for enhancing the accuracy, responsiveness, and efficiency of reliable roadside assistance and fast solutions for emergency breakdown states using the EF-YOLOv8m (Efficient - You Only Look Once version 8) algorithm. This proposed algorithm facilitates the visual prediction of breakdown situations and provides a fast solution for real-time prediction, analysis, and response in emergencies. The deployment of the EF - YOLOv8m algorithm leads to accurate prediction of vehicle breakdown situations, estimates road conditions, and detects critical faults to ensure the optimization of resource allocation and fast decision-making. Using its greater speed, accuracy, and lightweight model architecture, EE-YOLOv8 may process real-time image/video inputs and sensor data from vehicle-attached cameras, IoT devices, and surveillance drones in real time. Based on performance metrics such as confidence scores, detection accuracy, and frames per second (FPS), this model is used to analyse the reliability of EF-YOLOv8m in dynamic roadside environments. Additionally, the incorporation of AI -oriented and predictive maintenance algorithms improves the effectiveness of dispatch functions, reducing delay and guaranteeing timely assistance. Experimental results show the potential of YOLOv8m to transfigure the services of roadside assistance and provide an ascendable, high-performance solution that can address the

关键词： Resource allocation

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：