检索结果-内蒙古大学图书馆

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Sai Tejasree, K. Surendran, R. Rajakumar, B. Gomathi, R.M. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India J.N.N Institute of Engineering Department of Artificial Intelligence and Data Science Chennai India School of Computing Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509828

Clever system that can look at pictures of fruits and figure out what kind of fruit each picture shows. AI algorithms like deep learning, which is like giving the Machine learning model a crash course in fruit recognition. This method teaches the ML Model we clearly explained the Model using application's agent using PEAS and the application's task environment using the 6 dimensions by showing it tons of fruit images, so over time, it gets really good at spotting the differences and similarities between, say, a banana and a grape. We also used another technique called pattern recognition, which helps the computer pay attention to specific details like the fruit's color, shape, size and texture. Overcoming multiple obstacles in order to automatically identify the type of fruit from the picture. The variety of images is influencing the color, texture, and shape of many different types of fruits. When it came to fruit picture detection, Convolutional Neural Network (CNN) Algorithm outperformed standard support-vector-machine-based approaches using handcrafted features in terms of accuracy also, it is a lot faster to implement for new fruits. By integrating deep learning and pattern recognition techniques such as Convolutional Neural Network Algorithm we have got the accuracy of 84%, our system efficiently identified different fruit types from images, demonstrating the power and effectiveness of our methods. The goal of our project is to create a tool that can quickly and correctly identify many types of fruits in photos, which could be useful for things like sorting fruits in a grocery store or helping people learn about different fruits by using Convolutional Neural Network Algorithm. This is not just about teaching a computer to recognize fruits;it is about making technology that can understand and interact with the world in a way that is helpful to us. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise 38

Resfusion: Denoising Diffusion Probabilistic Models for Imag...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Shi, Zhenning Zheng, Haoshuai Xu, Chen Dong, Changsheng Pan, Bin Xie, Xueshuo He, Along Li, Tao Fu, Huazhu College of Computer Science Nankai University China School of Statistics and Data Science Nankai University China Haihe Lab of ITAI China Institute of High Performance Computing A*STAR Singapore

Recently, research on denoising diffusion models has expanded its application to the field of image restoration. Traditional diffusion-based image restoration methods utilize degraded images as conditional input to effectively guide the reverse generation process, without modifying the original denoising diffusion process. However, since the degraded images already include low-frequency information, starting from Gaussian white noise will result in increased sampling steps. We propose Resfusion, a general framework that incorporates the residual term into the diffusion forward process, starting the reverse process directly from the noisy degraded images. The form of our inference process is consistent with the DDPM. We introduced a weighted residual noise, named resnoise, as the prediction target and explicitly provide the quantitative relationship between the residual term and the noise term in resnoise. By leveraging a smooth equivalence transformation, Resfusion determine the optimal acceleration step and maintains the integrity of existing noise schedules, unifying the training and inference processes. The experimental results demonstrate that Resfusion exhibits competitive performance on ISTD dataset, LOL dataset and Raindrop dataset with only five sampling steps. Furthermore, Resfusion can be easily applied to image generation and emerges with strong versatility. Our code and model are available at https://***/nkicsl/Resfusion. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RoCEL: Advancing Table Entity Linking through Distinctive Row and Column Contexts

RoCEL: Advancing Table Entity Linking through Distinctive Ro...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Wang, Yuanzheng Fan, Yixing Guo, Jiafeng Zhang, Ruqing Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798891761643

Table entity linking (TEL) aims to map entity mentions in the table to their corresponding entities in a knowledge base (KB). The core of this task is to leverage structured contexts, specifically row and column contexts, to enhance the semantics of mentions in entity disambiguation. Most entity linking (EL) methods primarily focus on understanding sequential text contexts, making it difficult to adapt to the row and column structure of tables. Additionally, existing methods for TEL indiscriminately mix row and column contexts together, overlooking their semantic differences. In this paper, we explicitly distinguish the modeling of row and column contexts, and propose a method called RoCEL to capture their distinct semantics. Specifically, for row contexts in tables, we take the attention mechanism to learn the implicit relational dependencies between each cell and the mention. For column contexts in tables, we employ a set-wise encoder to learn the categorical information about the group of mentions. At last, we merge both contexts to obtain the final mention embedding for link prediction. Experiments on four benchmarks show that our approach outperforms the state-of-the-art (SOTA) baseline by about 1.5% on the in-domain dataset, and by 3.7% on average across three out-of-domain datasets. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition 38

LF-ViT: Reducing Spatial Redundancy in Vision Transformer fo...

引用

38th AAAI Conference on Artificial Intelligence, AAAI 2024

作者： Hu, Youbing Cheng, Yun Lu, Anqi Cao, Zhiqiang Wei, Dawei Liu, Jie Li, Zhijun AIoT Lab Faculty of Computing Harbin Institute of Technology China Swiss Data Science Center Zurich Switzerland School of Cyber Engineering Xidian University China

ISBN: (纸本)1577358872

The Vision Transformer (ViT) excels in accuracy when handling high-resolution images, yet it confronts the challenge of significant spatial redundancy, leading to increased computational and memory requirements. To address this, we present the Localization and Focus Vision Transformer (LF-ViT). This model operates by strategically curtailing computational demands without impinging on performance. In the Localization phase, a reduced-resolution image is processed;if a definitive prediction remains elusive, our pioneering Neighborhood Global Class Attention (NGCA) mechanism is triggered, effectively identifying and spotlighting class-discriminative regions based on initial findings. Subsequently, in the Focus phase, this designated region is used from the original image to enhance recognition. Uniquely, LF-ViT employs consistent parameters across both phases, ensuring seamless end-to-end optimization. Our empirical tests affirm LF-ViT's prowess: it remarkably decreases Deit-S's FLOPs by 63% and concurrently amplifies throughput twofold. Code of this project is at https://***/edgeai1/***. Copyright © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching 38

GoMatching: A Simple Baseline for Video Text Spotting via Lo...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： He, Haibin Ye, Maoyuan Zhang, Jing Liu, Juhua Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Wuhan University China College of Computing & Data Science Nanyang Technological University Singapore

Beyond the text detection and recognition tasks in image text spotting, video text spotting presents an augmented challenge with the inclusion of tracking. While advanced end-to-end trainable methods have shown commendable performance, the pursuit of multi-task optimization may pose the risk of producing sub-optimal outcomes for individual tasks. In this paper, we identify a main bottleneck in the state-of-the-art video text spotter: the limited recognition capability. In response to this issue, we propose to efficiently turn an off-the-shelf query-based image text spotter into a specialist on video and present a simple baseline termed GoMatching, which focuses the training efforts on tracking while maintaining strong recognition performance. To adapt the image text spotter to video datasets, we add a rescoring head to rescore each detected instance's confidence via efficient tuning, leading to a better tracking candidate pool. Additionally, we design a long-short term matching module, termed LST-Matcher, to enhance the spotter's tracking capability by integrating both long- and short-term matching results via Transformer. Based on the above simple designs, GoMatching delivers new records on ICDAR15-video, DSText, BOVText, and our proposed novel test set with arbitrary-shaped text termed ArTVideo, which demonstrates GoMatching's capability to accommodate general, dense, small, arbitrary-shaped, Chinese and English text scenarios while saving considerable training budgets. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Safer Roads: A Comprehensive Review of Object Detection Techniques for Autonomous Vehicles

引用

SN Computer science 2025年第5期6卷 1-20页

作者： Parisapogu, Samson Anosh Babu Narla, Nitya Juryala, Aarthi Ramavath, Siddhu Department of Computer Science and Engineering School of Computing Amrita Vishwa Vidyapeetham Amaravati Campus Andhra Pradesh Amaravati 522 503 India Department of Artificial Intelligence and Data Science Chaitanya Bharathi Institute of Technology Hyderabad 500075 India

Nowadays, people spend a lot of time in travel, and road safety has become an important area of research. As a result, self-driving cars have been gaining popularity in recent years because they have a lot of benefits in terms of reducing traffic congestion and improving road safety, thereby reducing accidents. They also have an environmental benefit as they reduce travel times and hence reduce the usage of fuel. Though a lot of research has already been done in this field, there are always new problems being created and new solutions being found. Apart from self-driving cars, automated navigation also has a huge number of applications. Therefore, it is important to stay up to date about the latest developments in this field. This research is a comprehensive survey that explores and evaluates the different object-detecting algorithms that have been used throughout the years, their advantages, disadvantages, and trade-offs. It also analyses the datasets and benchmarks that have been used for evaluating the models. It aims to identify the gaps in research in this growing field so that it can act as a roadmap for researchers to focus their study on. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning Object detection Road safety Self-driving YOLO

来源：评论

学校读者我要写书评

暂无评论

Detecting the Traceability Issues in Supply chain Industries using Blockchain Technology

Detecting the Traceability Issues in Supply chain Industries...

引用

2022 IEEE International Conference on Advances in computing, Communication and Applied Informatics, ACCAI 2022

作者： Subashini, B. Hemavathi, D. School of Computing SRM Institute of Science and Technology Department of Data Science and Business Systems India

ISBN: (纸本)9781665495295

Today, agriculture remains the most important economic activity in the world. Food care is a major concern for the whole society. For agriculture-based supply chain management, traceability is considered as the major requirement. Traceability helps in providing quality assurance and transparency to the end user. The antiquated traceability system has the complications of centralized systems, non-Transparency of information, unpredictable data, and the very easy formation of false data. The World Health Organization (WHO) reports that one out of ten people is affected by having tainted food. Globalization involving different food production processes and automation pushes the food supply chain into a complicated web. Numerous advancements have been investigated lately to determine food vulnerability and carry productivity to food related issues. One of the expected advances is block chain, which is as of now being effectively executed in monetary areas, for example, bit coin. Block chain can also be used in the food supply chain industries to improve traceability and help in the danger decrease of fakes and different types of unlawful occupation. This paper presents a systematic survey on agrifood supply chain traceability issues using various block chain platforms such as Ethereum and Hyperledger, as well as IOT techniques such as barcodes, RFID, NFC, and QR codes. The performance of several consensus algorithms is also investigated. © 2022 IEEE.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

Smart Home Based on IoT by Using Machine Learning 1

引用

6th International Conference on Microelectronics and Telecommunication Engineering, ICMETE 2022

作者： Lavanya, K. Archana, K.S. CSE Vels Institute of Science Technology & Advanced Studies Chennai India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (数字)9789811995125

ISBN: (纸本)9789811995118

Smart homes have surfaced as the coming wave of technological advancement. It is a collection of smaller systems connected to home network and comprising a variety of communication technologies which can assist inhabitants’ convenience, security, safety, and comfort. This paper examines several IoT based smart house approaches, which were divided as 2 categories depending on application: smart home security system and smart home automation. We explored several sensors, doors, and communication protocols utilized in IoT-based smart homes in this paper. We also discussed about research problems and also open research objectives. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Cirrhosis Prediction in Chronic Liver Disease Patients Using Machine Learning Techniques 3

Cirrhosis Prediction in Chronic Liver Disease Patients Using...

引用

3rd International Conference on Pervasive computing and Social Networking, ICPCSN 2023

作者： Athish, V.P. Sree Nandha, S.S. Rajeswari, D. School of Computing College of Engineering and Technology Srm Institute of Science and Technology Dept. of Data Science and Business Systems Tamilnadu Kattankulathur603203 India

ISBN: (纸本)9798350322842

Liver failure is a serious medical condition that can have life-threatening consequences. The liver is responsible for filtering blood and performing many other important functions. With the rise of machine learning in healthcare, there is an opportunity to use past datasets to predict liver failure early on. The main focus of this research work is to explore the application of supervised machine learning algorithms in predicting liver failure. The study involved pre-processing techniques such as univariate and bivariate analysis, and data visualization to gain better insights into the features of the dataset. Using these techniques, a multi-class classification model was built with machine learning algorithms, and the performance metrics of accuracy, F1 score, and recall were used to compare the algorithms. The results show that machine learning algorithms can accurately predict liver failure and can be an effective tool in healthcare. This study demonstrates the potential of machine learning in predicting liver failure and can contribute to the development of future models in the field. The results of this research study indicates that the proposed algorithm achieved an accuracy of 94.48%. The proposed work will be beneficial to researchers in this field and inspire them to build more advanced and accurate models. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Deriving Pipeline for Emergency Services Using Natural Language Processing Techniques 11th

Deriving Pipeline for Emergency Services Using Natural Langu...

引用

11th International Conference on Recent Trends in computing, ICRTC 2022

作者： Anand, Akshat Rajeswari, D. Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Chennai603203 India

ISBN: (纸本)9789811988240

Communications have a crucial role in times of crisis, particularly in times of emergency. Whenever a region is affected by any disaster, social media sites such as Twitter, etc., are a great way to get information out to those who need it the most. Our paper suggests that in times of crisis, when people are worried about finding the right emergency contacts or are experiencing a transformation in their psychological response, they should manually enter their experience into an app to obtain contact information for the nearest SOS. Alternatively, the proposed application suggests scraping hashtags from around the world with web scraping scripts to retrieve geo-referenced tweets in real time. In order to gather accurate data, Twitter's API or some third-party application can be used in the development of this software. When there is a major crisis, social media user behavior plays a vital role, owing to its efficiency and high reliability with swift data dissemination. Anxiety over finding the right emergency team contact may cause people to lose their cool and become unclear about which authority they should call when an emergency occurs. Eventually, our application bridges the gap between clients in need of help and the approved agency that can really provide that support in different circumstances. In the case of, for example, a lost child or a flooded area, our application helps you get in touch with an organization that can assist you in dealing with the situation. We have used CNN-1-D + LSTM, CNN-1-D + Bi-LSTMs, and CNN-1-D + LSTM + Glove-100-D to get maximum accuracy for the classification model. It is possible to use the prototype solution in a novel way to organize immediate assistance with authorities in comprehensive administration, while integrating Twitter or other social platforms into the application can make it a feasible platform for preventive intervention and catastrophe management. © 2023, The Author(s), under exclusive license to Springer Nature

关键词： Emergency services

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：